20220427.md

ArXiv cs.CV --Wed, 27 Apr 2022

1.Sound Localization by Self-Supervised Time Delay Estimation ⬇️

Sounds reach one microphone in a stereo pair sooner than the other, resulting in an interaural time delay that conveys their directions. Estimating a sound's time delay requires finding correspondences between the signals recorded by each microphone. We propose to learn these correspondences through self-supervision, drawing on recent techniques from visual tracking. We adapt the contrastive random walk of Jabri et al. to learn a cycle-consistent representation from unlabeled stereo sounds, resulting in a model that performs on par with supervised methods on "in the wild" internet recordings. We also propose a multimodal contrastive learning model that solves a visually-guided localization task: estimating the time delay for a particular person in a multi-speaker mixture, given a visual representation of their face. Project site: this https URL

2.ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation ⬇️

Recently, customized vision transformers have been adapted for human pose estimation and have achieved superior performance with elaborate structures. However, it is still unclear whether plain vision transformers can facilitate pose estimation. In this paper, we take the first step toward answering the question by employing a plain and non-hierarchical vision transformer together with simple deconvolution decoders termed ViTPose for human pose estimation. We demonstrate that a plain vision transformer with MAE pretraining can obtain superior performance after finetuning on human pose estimation datasets. ViTPose has good scalability with respect to model size and flexibility regarding input resolution and token number. Moreover, it can be easily pretrained using the unlabeled pose data without the need for large-scale upstream ImageNet data. Our biggest ViTPose model based on the ViTAE-G backbone with 1 billion parameters obtains the best 80.9 mAP on the MS COCO test-dev set, while the ensemble models further set a new state-of-the-art for human pose estimation, i.e., 81.1 mAP. The source code and models will be released at this https URL.

3.Focal Sparse Convolutional Networks for 3D Object Detection ⬇️

Non-uniformed 3D sparse data, e.g., point clouds or voxels in different spatial positions, make contribution to the task of 3D object detection in different ways. Existing basic components in sparse convolutional networks (Sparse CNNs) process all sparse data, regardless of regular or submanifold sparse convolution. In this paper, we introduce two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction. They are focal sparse convolution (Focals Conv) and its multi-modal variant of focal sparse convolution with fusion, or Focals Conv-F for short. The new modules can readily substitute their plain counterparts in existing Sparse CNNs and be jointly trained in an end-to-end fashion. For the first time, we show that spatially learnable sparsity in sparse convolution is essential for sophisticated 3D object detection. Extensive experiments on the KITTI, nuScenes and Waymo benchmarks validate the effectiveness of our approach. Without bells and whistles, our results outperform all existing single-model entries on the nuScenes test benchmark at the paper submission time. Code and models are at this https URL.

4.Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images ⬇️

Multiple Instance Learning (MIL) methods have become increasingly popular for classifying giga-pixel sized Whole-Slide Images (WSIs) in digital pathology. Most MIL methods operate at a single WSI magnification, by processing all the tissue patches. Such a formulation induces high computational requirements, and constrains the contextualization of the WSI-level representation to a single scale. A few MIL methods extend to multiple scales, but are computationally more demanding. In this paper, inspired by the pathological diagnostic process, we propose ZoomMIL, a method that learns to perform multi-level zooming in an end-to-end manner. ZoomMIL builds WSI representations by aggregating tissue-context information from multiple magnifications. The proposed method outperforms the state-of-the-art MIL methods in WSI classification on two large datasets, while significantly reducing the computational demands with regard to Floating-Point Operations (FLOPs) and processing time by up to 40x.

5.Understanding The Robustness in Vision Transformers ⬇️

Recent studies show that Vision Transformers(ViTs) exhibit strong robustness against various corruptions. Although this property is partly attributed to the self-attention mechanism, there is still a lack of systematic understanding. In this paper, we examine the role of self-attention in learning robust representations. Our study is motivated by the intriguing properties of the emerging visual grouping in Vision Transformers, which indicates that self-attention may promote robustness through improved mid-level representations. We further propose a family of fully attentional networks (FANs) that strengthen this capability by incorporating an attentional channel processing design. We validate the design comprehensively on various hierarchical backbones. Our model achieves a state of-the-art 87.1% accuracy and 35.8% mCE on ImageNet-1k and ImageNet-C with 76.8M parameters. We also demonstrate state-of-the-art accuracy and robustness in two downstream tasks: semantic segmentation and object detection. Code will be available at this https URL.

6.MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval ⬇️

Dominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations, but ignore detailed local semantics. The recent success of image BERT pre-training with masked visual modeling that promotes the learning of local visual context, motivates a possible solution to address the above limitation. In this work, we for the first time investigate masked visual modeling in video-text pre-training with the "dual-encoder" architecture. We perform Masked visual modeling with Injected LanguagE Semantics (MILES) by employing an extra snapshot video encoder as an evolving "tokenizer" to produce reconstruction targets for masked video patch prediction. Given the corrupted video, the video encoder is trained to recover text-aligned features of the masked patches via reasoning with the visible regions along the spatial and temporal dimensions, which enhances the discriminativeness of local visual features and the fine-grained cross-modality alignment. Our method outperforms state-of-the-art methods for text-to-video retrieval on four datasets with both zero-shot and fine-tune evaluation protocols. Our approach also surpasses the baseline models significantly on zero-shot action recognition, which can be cast as video-to-text retrieval.

7.A survey on attention mechanisms for medical applications: are we moving towards better algorithms? ⬇️

The increasing popularity of attention mechanisms in deep learning algorithms for computer vision and natural language processing made these models attractive to other research domains. In healthcare, there is a strong need for tools that may improve the routines of the clinicians and the patients. Naturally, the use of attention-based algorithms for medical applications occurred smoothly. However, being healthcare a domain that depends on high-stake decisions, the scientific community must ponder if these high-performing algorithms fit the needs of medical applications. With this motto, this paper extensively reviews the use of attention mechanisms in machine learning (including Transformers) for several medical applications. This work distinguishes itself from its predecessors by proposing a critical analysis of the claims and potentialities of attention mechanisms presented in the literature through an experimental case study on medical image classification with three different use cases. These experiments focus on the integrating process of attention mechanisms into established deep learning architectures, the analysis of their predictive power, and a visual assessment of their saliency maps generated by post-hoc explanation methods. This paper concludes with a critical analysis of the claims and potentialities presented in the literature about attention mechanisms and proposes future research lines in medical applications that may benefit from these frameworks.

8.Understanding the Impact of Edge Cases from Occluded Pedestrians for ML Systems ⬇️

Machine learning (ML)-enabled approaches are considered a substantial support technique of detection and classification of obstacles of traffic participants in self-driving vehicles. Major breakthroughs have been demonstrated the past few years, even covering complete end-to-end data processing chain from sensory inputs through perception and planning to vehicle control of acceleration, breaking and steering. YOLO (you-only-look-once) is a state-of-the-art perception neural network (NN) architecture providing object detection and classification through bounding box estimations on camera images. As the NN is trained on well annotated images, in this paper we study the variations of confidence levels from the NN when tested on hand-crafted occlusion added to a test set. We compare regular pedestrian detection to upper and lower body detection. Our findings show that the two NN using only partial information perform similarly well like the NN for the full body when the full body NN's performance is 0.75 or better. Furthermore and as expected, the network, which is only trained on the lower half body is least prone to disturbances from occlusions of the upper half and vice versa.

9.ROMA: Cross-Domain Region Similarity Matching for Unpaired Nighttime Infrared to Daytime Visible Video Translation ⬇️

Infrared cameras are often utilized to enhance the night vision since the visible light cameras exhibit inferior efficacy without sufficient illumination. However, infrared data possesses inadequate color contrast and representation ability attributed to its intrinsic heat-related imaging principle. This makes it arduous to capture and analyze information for human beings, meanwhile hindering its application. Although, the domain gaps between unpaired nighttime infrared and daytime visible videos are even huger than paired ones that captured at the same time, establishing an effective translation mapping will greatly contribute to various fields. In this case, the structural knowledge within nighttime infrared videos and semantic information contained in the translated daytime visible pairs could be utilized simultaneously. To this end, we propose a tailored framework ROMA that couples with our introduced cRoss-domain regiOn siMilarity mAtching technique for bridging the huge gaps. To be specific, ROMA could efficiently translate the unpaired nighttime infrared videos into fine-grained daytime visible ones, meanwhile maintain the spatiotemporal consistency via matching the cross-domain region similarity. Furthermore, we design a multiscale region-wise discriminator to distinguish the details from synthesized visible results and real references. Extensive experiments and evaluations for specific applications indicate ROMA outperforms the state-of-the-art methods. Moreover, we provide a new and challenging dataset encouraging further research for unpaired nighttime infrared and daytime visible video translation, named InfraredCity. In particular, it consists of 9 long video clips including City, Highway and Monitor scenarios. All clips could be split into 603,142 frames in total, which are 20 times larger than the recently released daytime infrared-to-visible dataset IRVI.

10.Causal Transportability for Visual Recognition ⬇️

Visual representations underlie object recognition tasks, but they often contain both robust and non-robust features. Our main observation is that image classifiers may perform poorly on out-of-distribution samples because spurious correlations between non-robust features and labels can be changed in a new environment. By analyzing procedures for out-of-distribution generalization with a causal graph, we show that standard classifiers fail because the association between images and labels is not transportable across settings. However, we then show that the causal effect, which severs all sources of confounding, remains invariant across domains. This motivates us to develop an algorithm to estimate the causal effect for image classification, which is transportable (i.e., invariant) across source and target environments. Without observing additional variables, we show that we can derive an estimand for the causal effect under empirical assumptions using representations in deep models as proxies. Theoretical analysis, empirical results, and visualizations show that our approach captures causal invariances and improves overall generalization.

11.Restricted Black-box Adversarial Attack Against DeepFake Face Swapping ⬇️

DeepFake face swapping presents a significant threat to online security and social media, which can replace the source face in an arbitrary photo/video with the target face of an entirely different person. In order to prevent this fraud, some researchers have begun to study the adversarial methods against DeepFake or face manipulation. However, existing works focus on the white-box setting or the black-box setting driven by abundant queries, which severely limits the practical application of these methods. To tackle this problem, we introduce a practical adversarial attack that does not require any queries to the facial image forgery model. Our method is built on a substitute model persuing for face reconstruction and then transfers adversarial examples from the substitute model directly to inaccessible black-box DeepFake models. Specially, we propose the Transferable Cycle Adversary Generative Adversarial Network (TCA-GAN) to construct the adversarial perturbation for disrupting unknown DeepFake systems. We also present a novel post-regularization module for enhancing the transferability of generated adversarial examples. To comprehensively measure the effectiveness of our approaches, we construct a challenging benchmark of DeepFake adversarial attacks for future development. Extensive experiments impressively show that the proposed adversarial attack method makes the visual quality of DeepFake face images plummet so that they are easier to be detected by humans and algorithms. Moreover, we demonstrate that the proposed algorithm can be generalized to offer face image protection against various face translation methods.

12.Generating Topological Structure of Floorplans from Room Attributes ⬇️

Analysis of indoor spaces requires topological information. In this paper, we propose to extract topological information from room attributes using what we call Iterative and adaptive graph Topology Learning (ITL). ITL progressively predicts multiple relations between rooms; at each iteration, it improves node embeddings, which in turn facilitates generation of a better topological graph structure. This notion of iterative improvement of node embeddings and topological graph structure is in the same spirit as \cite{chen2020iterative}. However, while \cite{chen2020iterative} computes the adjacency matrix based on node similarity, we learn the graph metric using a relational decoder to extract room correlations. Experiments using a new challenging indoor dataset validate our proposed method. Qualitative and quantitative evaluation for layout topology prediction and floorplan generation applications also demonstrate the effectiveness of ITL.

13.RAPQ: Rescuing Accuracy for Power-of-Two Low-bit Post-training Quantization ⬇️

We introduce a Power-of-Two post-training quantization( PTQ) method for deep neural network that meets hardware requirements and does not call for long-time retraining. PTQ requires a small set of calibration data and is easier for deployment, but results in lower accuracy than Quantization-Aware Training( QAT). Power-of-Two quantization can convert the multiplication introduced by quantization and dequantization to bit-shift that is adopted by many efficient accelerators. However, the Power-of-Two scale has fewer candidate values, which leads to more rounding or clipping errors. We propose a novel Power-of-Two PTQ framework, dubbed RAPQ, which dynamically adjusts the Power-of-Two scales of the whole network instead of statically determining them layer by layer. It can theoretically trade off the rounding error and clipping error of the whole network. Meanwhile, the reconstruction method in RAPQ is based on the BN information of every unit. Extensive experiments on ImageNet prove the excellent performance of our proposed method. Without bells and whistles, RAPQ can reach accuracy of 65% and 48% on ResNet-18 and MobileNetV2 respectively with weight INT2 activation INT4. We are the first to propose PTQ for the more constrained but hardware-friendly Power-of-Two quantization and prove that it can achieve nearly the same accuracy as SOTA PTQ method. The code will be released.

14.Evaluating the Quality of a Synthesized Motion with the Fréchet Motion Distance ⬇️

Evaluating the Quality of a Synthesized Motion with the Fréchet Motion Distance

15.Unified GCNs: Towards Connecting GCNs with CNNs ⬇️

Graph Convolutional Networks (GCNs) have been widely demonstrated their powerful ability in graph data representation and learning. Existing graph convolution layers are mainly designed based on graph signal processing and transform aspect which usually suffer from some limitations, such as over-smoothing, over-squashing and non-robustness, etc. As we all know that Convolution Neural Networks (CNNs) have received great success in many computer vision and machine learning. One main aspect is that CNNs leverage many learnable convolution filters (kernels) to obtain rich feature descriptors and thus can have high capacity to encode complex patterns in visual data analysis. Also, CNNs are flexible in designing their network architecture, such as MobileNet, ResNet, Xception, etc. Therefore, it is natural to arise a question: can we design graph convolutional layer as flexibly as that in CNNs? Innovatively, in this paper, we consider connecting GCNs with CNNs deeply from a general perspective of depthwise separable convolution operation. Specifically, we show that GCN and GAT indeed perform some specific depthwise separable convolution operations. This novel interpretation enables us to better understand the connections between GCNs (GCN, GAT) and CNNs and further inspires us to design more Unified GCNs (UGCNs). As two showcases, we implement two UGCNs, i.e., Separable UGCN (S-UGCN) and General UGCN (G-UGCN) for graph data representation and learning. Promising experiments on several graph representation benchmarks demonstrate the effectiveness and advantages of the proposed UGCNs.

16.Unsupervised Segmentation of Hyperspectral Remote Sensing Images with Superpixels ⬇️

In this paper, we propose an unsupervised method for hyperspectral remote sensing image segmentation. The method exploits the mean-shift clustering algorithm that takes as input a preliminary hyperspectral superpixels segmentation together with the spectral pixel information. The proposed method does not require the number of segmentation classes as input parameter, and it does not exploit any a-priori knowledge about the type of land-cover or land-use to be segmented (e.g. water, vegetation, building etc.). Experiments on Salinas, SalinasA, Pavia Center and Pavia University datasets are carried out. Performance are measured in terms of normalized mutual information, adjusted Rand index and F1-score. Results demonstrate the validity of the proposed method in comparison with the state of the art.

17.Contrastive Language-Action Pre-training for Temporal Localization ⬇️

Long-form video understanding requires designing approaches that are able to temporally localize activities or language. End-to-end training for such tasks is limited by the compute device memory constraints and lack of temporal annotations at large-scale. These limitations can be addressed by pre-training on large datasets of temporally trimmed videos supervised by class annotations. Once the video encoder is pre-trained, it is common practice to freeze it during fine-tuning. Therefore, the video encoder does not learn temporal boundaries and unseen classes, causing a domain gap with respect to the downstream tasks. Moreover, using temporally trimmed videos prevents to capture the relations between different action categories and the background context in a video clip which results in limited generalization capacity. To address these limitations, we propose a novel post-pre-training approach without freezing the video encoder which leverages language. We introduce a masked contrastive learning loss to capture visio-linguistic relations between activities, background video clips and language in the form of captions. Our experiments show that the proposed approach improves the state-of-the-art on temporal action localization, few-shot temporal action localization, and video language grounding tasks.

18.Data-Efficient Backdoor Attacks ⬇️

Recent studies have proven that deep neural networks are vulnerable to backdoor attacks. Specifically, by mixing a small number of poisoned samples into the training set, the behavior of the trained model can be maliciously controlled. Existing attack methods construct such adversaries by randomly selecting some clean data from the benign set and then embedding a trigger into them. However, this selection strategy ignores the fact that each poisoned sample contributes inequally to the backdoor injection, which reduces the efficiency of poisoning. In this paper, we formulate improving the poisoned data efficiency by the selection as an optimization problem and propose a Filtering-and-Updating Strategy (FUS) to solve it. The experimental results on CIFAR-10 and ImageNet-10 indicate that the proposed method is effective: the same attack success rate can be achieved with only 47% to 75% of the poisoned sample volume compared to the random selection strategy. More importantly, the adversaries selected according to one setting can generalize well to other settings, exhibiting strong transferability.

19.Attentive Fine-Grained Structured Sparsity for Image Restoration ⬇️

Image restoration tasks have witnessed great performance improvement in recent years by developing large deep models. Despite the outstanding performance, the heavy computation demanded by the deep models has restricted the application of image restoration. To lift the restriction, it is required to reduce the size of the networks while maintaining accuracy. Recently, N:M structured pruning has appeared as one of the effective and practical pruning approaches for making the model efficient with the accuracy constraint. However, it fails to account for different computational complexities and performance requirements for different layers of an image restoration network. To further optimize the trade-off between the efficiency and the restoration accuracy, we propose a novel pruning method that determines the pruning ratio for N:M structured sparsity at each layer. Extensive experimental results on super-resolution and deblurring tasks demonstrate the efficacy of our method which outperforms previous pruning methods significantly. PyTorch implementation for the proposed methods will be publicly available at this https URL.

20.Intercategorical Label Interpolation for Emotional Face Generation with Conditional Generative Adversarial Networks ⬇️

Generative adversarial networks offer the possibility to generate deceptively real images that are almost indistinguishable from actual photographs. Such systems however rely on the presence of large datasets to realistically replicate the corresponding domain. This is especially a problem if not only random new images are to be generated, but specific (continuous) features are to be co-modeled. A particularly important use case in \emph{Human-Computer Interaction} (HCI) research is the generation of emotional images of human faces, which can be used for various use cases, such as the automatic generation of avatars. The problem hereby lies in the availability of training data. Most suitable datasets for this task rely on categorical emotion models and therefore feature only discrete annotation labels. This greatly hinders the learning and modeling of smooth transitions between displayed affective states. To overcome this challenge, we explore the potential of label interpolation to enhance networks trained on categorical datasets with the ability to generate images conditioned on continuous features.

21.Context-Aware Sequence Alignment using 4D Skeletal Augmentation ⬇️

Temporal alignment of fine-grained human actions in videos is important for numerous applications in computer vision, robotics, and mixed reality. State-of-the-art methods directly learn image-based embedding space by leveraging powerful deep convolutional neural networks. While being straightforward, their results are far from satisfactory, the aligned videos exhibit severe temporal discontinuity without additional post-processing steps. The recent advancements in human body and hand pose estimation in the wild promise new ways of addressing the task of human action alignment in videos. In this work, based on off-the-shelf human pose estimators, we propose a novel context-aware self-supervised learning architecture to align sequences of actions. We name it CASA. Specifically, CASA employs self-attention and cross-attention mechanisms to incorporate the spatial and temporal context of human actions, which can solve the temporal discontinuity problem. Moreover, we introduce a self-supervised learning scheme that is empowered by novel 4D augmentation techniques for 3D skeleton representations. We systematically evaluate the key components of our method. Our experiments on three public datasets demonstrate CASA significantly improves phase progress and Kendall's Tau scores over the previous state-of-the-art methods.

22.Boosting Adversarial Transferability of MLP-Mixer ⬇️

The security of models based on new architectures such as MLP-Mixer and ViTs needs to be studied urgently. However, most of the current researches are mainly aimed at the adversarial attack against ViTs, and there is still relatively little adversarial work on MLP-mixer. We propose an adversarial attack method against MLP-Mixer called Maxwell's demon Attack (MA). MA breaks the channel-mixing and token-mixing mechanism of MLP-Mixer by controlling the part input of MLP-Mixer's each Mixer layer, and disturbs MLP-Mixer to obtain the main information of images. Our method can mask the part input of the Mixer layer, avoid overfitting of the adversarial examples to the source model, and improve the transferability of cross-architecture. Extensive experimental evaluation demonstrates the effectiveness and superior performance of the proposed MA. Our method can be easily combined with existing methods and can improve the transferability by up to 38.0% on MLP-based ResMLP. Adversarial examples produced by our method on MLP-Mixer are able to exceed the transferability of adversarial examples produced using DenseNet against CNNs. To the best of our knowledge, we are the first work to study adversarial transferability of MLP-Mixer.

23.Urban Change Detection Using a Dual-Task Siamese Network and Semi-Supervised Learning ⬇️

In this study, a Semi-Supervised Learning (SSL) method for improving urban change detection from bi-temporal image pairs was presented. The proposed method adapted a Dual-Task Siamese Difference network that not only predicts changes with the difference decoder, but also segments buildings for both images with a semantics decoder. First, the architecture was modified to produce a second change prediction derived from the semantics predictions. Second, SSL was adopted to improve supervised change detection. For unlabeled data, we introduced a loss that encourages the network to predict consistent changes across the two change outputs. The proposed method was tested on urban change detection using the SpaceNet7 dataset. SSL achieved improved results compared to three fully supervised benchmarks.

24.Adaptive Split-Fusion Transformer ⬇️

Neural networks for visual content understanding have recently evolved from convolutional ones (CNNs) to transformers. The prior (CNN) relies on small-windowed kernels to capture the regional clues, demonstrating solid local expressiveness. On the contrary, the latter (transformer) establishes long-range global connections between localities for holistic learning. Inspired by this complementary nature, there is a growing interest in designing hybrid models to best utilize each technique. Current hybrids merely replace convolutions as simple approximations of linear projection or juxtapose a convolution branch with attention, without concerning the importance of local/global modeling. To tackle this, we propose a new hybrid named Adaptive Split-Fusion Transformer (ASF-former) to treat convolutional and attention branches differently with adaptive weights. Specifically, an ASF-former encoder equally splits feature channels into half to fit dual-path inputs. Then, the outputs of dual-path are fused with weighting scalars calculated from visual cues. We also design the convolutional path compactly for efficiency concerns. Extensive experiments on standard benchmarks, such as ImageNet-1K, CIFAR-10, and CIFAR-100, show that our ASF-former outperforms its CNN, transformer counterparts, and hybrid pilots in terms of accuracy (83.9% on ImageNet-1K), under similar conditions (12.9G MACs/56.7M Params, without large-scale pre-training). The code is available at: this https URL.

25.Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams ⬇️

Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented from leveraging large fully-annotated dataset, but rather the interactions with supervisory signals are sparsely distributed over space and time. This paper proposes a novel neural-network-based approach to progressively and autonomously develop pixel-wise representations in a video stream. The proposed method is based on a human-like attention mechanism that allows the agent to learn by observing what is moving in the attended locations. Spatio-temporal stochastic coherence along the attention trajectory, paired with a contrastive term, leads to an unsupervised learning criterion that naturally copes with the considered setting. Differently from most existing works, the learned representations are used in open-set class-incremental classification of each frame pixel, relying on few supervisions. Our experiments leverage 3D virtual environments and they show that the proposed agents can learn to distinguish objects just by observing the video stream. Inheriting features from state-of-the art models is not as powerful as one might expect.

26.TranSiam: Fusing Multimodal Visual Features Using Transformer for Medical Image Segmentation ⬇️

Automatic segmentation of medical images based on multi-modality is an important topic for disease diagnosis. Although the convolutional neural network (CNN) has been proven to have excellent performance in image segmentation tasks, it is difficult to obtain global information. The lack of global information will seriously affect the accuracy of the segmentation results of the lesion area. In addition, there are visual representation differences between multimodal data of the same patient. These differences will affect the results of the automatic segmentation methods. To solve these problems, we propose a segmentation method suitable for multimodal medical images that can capture global information, named TranSiam. TranSiam is a 2D dual path network that extracts features of different modalities. In each path, we utilize convolution to extract detailed information in low level stage, and design a ICMT block to extract global information in high level stage. ICMT block embeds convolution in the transformer, which can extract global information while retaining spatial and detailed information. Furthermore, we design a novel fusion mechanism based on cross attention and selfattention, called TMM block, which can effectively fuse features between different modalities. On the BraTS 2019 and BraTS 2020 multimodal datasets, we have a significant improvement in accuracy over other popular methods.

27.ClothFormer:Taming Video Virtual Try-on in All Module ⬇️

The task of video virtual try-on aims to fit the target clothes to a person in the video with spatio-temporal consistency. Despite tremendous progress of image virtual try-on, they lead to inconsistency between frames when applied to videos. Limited work also explored the task of video-based virtual try-on but failed to produce visually pleasing and temporally coherent results. Moreover, there are two other key challenges: 1) how to generate accurate warping when occlusions appear in the clothing region; 2) how to generate clothes and non-target body parts (e.g. arms, neck) in harmony with the complicated background; To address them, we propose a novel video virtual try-on framework, ClothFormer, which successfully synthesizes realistic, harmonious, and spatio-temporal consistent results in complicated environment. In particular, ClothFormer involves three major modules. First, a two-stage anti-occlusion warping module that predicts an accurate dense flow mapping between the body regions and the clothing regions. Second, an appearance-flow tracking module utilizes ridge regression and optical flow correction to smooth the dense flow sequence and generate a temporally smooth warped clothing sequence. Third, a dual-stream transformer extracts and fuses clothing textures, person features, and environment information to generate realistic try-on videos. Through rigorous experiments, we demonstrate that our method highly surpasses the baselines in terms of synthesized video quality both qualitatively and quantitatively.

28.Where and What: Driver Attention-based Object Detection ⬇️

Human drivers use their attentional mechanisms to focus on critical objects and make decisions while driving. As human attention can be revealed from gaze data, capturing and analyzing gaze information has emerged in recent years to benefit autonomous driving technology. Previous works in this context have primarily aimed at predicting "where" human drivers look at and lack knowledge of "what" objects drivers focus on. Our work bridges the gap between pixel-level and object-level attention prediction. Specifically, we propose to integrate an attention prediction module into a pretrained object detection framework and predict the attention in a grid-based style. Furthermore, critical objects are recognized based on predicted attended-to areas. We evaluate our proposed method on two driver attention datasets, BDD-A and DR(eye)VE. Our framework achieves competitive state-of-the-art performance in the attention prediction on both pixel-level and object-level but is far more efficient (75.3 GFLOPs less) in computation.

29.Deeper Insights into ViTs Robustness towards Common Corruptions ⬇️

Recent literature have shown design strategies from Convolutions Neural Networks (CNNs) benefit Vision Transformers (ViTs) in various vision tasks. However, it remains unclear how these design choices impact on robustness when transferred to ViTs. In this paper, we make the first attempt to investigate how CNN-like architectural designs and CNN-based data augmentation strategies impact on ViTs' robustness towards common corruptions through an extensive and rigorous benchmarking. We demonstrate that overlapping patch embedding and convolutional Feed-Forward Network (FFN) boost performance on robustness. Furthermore, adversarial noise training is powerful on ViTs while fourier-domain augmentation fails. Moreover, we introduce a novel conditional method enabling input-varied augmentations from two angles: (1) Generating dynamic augmentation parameters conditioned on input images. It conduces to state-of-the-art performance on robustness through conditional convolutions; (2) Selecting most suitable augmentation strategy by an extra predictor helps to achieve the best trade-off between clean accuracy and robustness.

30.Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring ⬇️

Real-world dynamic scene deblurring has long been a challenging task since paired blurry-sharp training data is unavailable. Conventional Maximum A Posteriori estimation and deep learning-based deblurring methods are restricted by handcrafted priors and synthetic blurry-sharp training pairs respectively, thereby failing to generalize to real dynamic blurriness. To this end, we propose a Neural Maximum A Posteriori (NeurMAP) estimation framework for training neural networks to recover blind motion information and sharp content from unpaired data. The proposed NeruMAP consists of a motion estimation network and a deblurring network which are trained jointly to model the (re)blurring process (i.e. likelihood function). Meanwhile, the motion estimation network is trained to explore the motion information in images by applying implicit dynamic motion prior, and in return enforces the deblurring network training (i.e. providing sharp image prior). The proposed NeurMAP is an orthogonal approach to existing deblurring neural networks, and is the first framework that enables training image deblurring networks on unpaired datasets. Experiments demonstrate our superiority on both quantitative metrics and visual quality over state-of-the-art methods. Codes are available on this https URL.

31.Instance-Specific Feature Propagation for Referring Segmentation ⬇️

Referring segmentation aims to generate a segmentation mask for the target instance indicated by a natural language expression. There are typically two kinds of existing methods: one-stage methods that directly perform segmentation on the fused vision and language features; and two-stage methods that first utilize an instance segmentation model for instance proposal and then select one of these instances via matching them with language features. In this work, we propose a novel framework that simultaneously detects the target-of-interest via feature propagation and generates a fine-grained segmentation mask. In our framework, each instance is represented by an Instance-Specific Feature (ISF), and the target-of-referring is identified by exchanging information among all ISFs using our proposed Feature Propagation Module (FPM). Our instance-aware approach learns the relationship among all objects, which helps to better locate the target-of-interest than one-stage methods. Comparing to two-stage methods, our approach collaboratively and interactively utilizes both vision and language information for synchronous identification and segmentation. In the experimental tests, our method outperforms previous state-of-the-art methods on all three RefCOCO series datasets.

32.Learning Dual-Pixel Alignment for Defocus Deblurring ⬇️

It is a challenging task to recover all-in-focus image from a single defocus blurry image in real-world applications. On many modern cameras, dual-pixel (DP) sensors create two-image views, based on which stereo information can be exploited to benefit defocus deblurring. Despite existing DP defocus deblurring methods achieving impressive results, they directly take naive concatenation of DP views as input, while neglecting the disparity between left and right views in the regions out of camera's depth of field (DoF). In this work, we propose a Dual-Pixel Alignment Network (DPANet) for defocus deblurring. Generally, DPANet is an encoder-decoder with skip-connections, where two branches with shared parameters in the encoder are employed to extract and align deep features from left and right views, and one decoder is adopted to fuse aligned features for predicting the all-in-focus image. Due to that DP views suffer from different blur amounts, it is not trivial to align left and right views. To this end, we propose novel encoder alignment module (EAM) and decoder alignment module (DAM). In particular, a correlation layer is suggested in EAM to measure the disparity between DP views, whose deep features can then be accordingly aligned using deformable convolutions. And DAM can further enhance the alignment of skip-connected features from encoder and deep features in decoder. By introducing several EAMs and DAMs, DP views in DPANet can be well aligned for better predicting latent all-in-focus image. Experimental results on real-world datasets show that our DPANet is notably superior to state-of-the-art deblurring methods in reducing defocus blur while recovering visually plausible sharp structures and textures.

33.U-Net with ResNet Backbone for Garment Landmarking Purpose ⬇️

We build a heatmap-based landmark detection model to locate important landmarks on 2D RGB garment images. The main goal is to detect edges, corners and suitable interior region of the garments. This let us re-create 3D garments in modern 3D editing software by incorporate landmark detection model and texture unwrapping. We use a U-net architecture with ResNet backbone to build the model. With an appropriate loss function, we are able to train a moderately robust model.

34.An Overview of Recent Work in Media Forensics: Methods and Threats ⬇️

In this paper, we review recent work in media forensics for digital images, video, audio (specifically speech), and documents. For each data modality, we discuss synthesis and manipulation techniques that can be used to create and modify digital media. We then review technological advancements for detecting and quantifying such manipulations. Finally, we consider open issues and suggest directions for future research.

35.Self-recoverable Adversarial Examples: A New Effective Protection Mechanism in Social Networks ⬇️

Malicious intelligent algorithms greatly threaten the security of social users' privacy by detecting and analyzing the uploaded photos to social network platforms. The destruction to DNNs brought by the adversarial attack sparks the potential that adversarial examples serve as a new protection mechanism for privacy security in social networks. However, the existing adversarial example does not have recoverability for serving as an effective protection mechanism. To address this issue, we propose a recoverable generative adversarial network to generate self-recoverable adversarial examples. By modeling the adversarial attack and recovery as a united task, our method can minimize the error of the recovered examples while maximizing the attack ability, resulting in better recoverability of adversarial examples. To further boost the recoverability of these examples, we exploit a dimension reducer to optimize the distribution of adversarial perturbation. The experimental results prove that the adversarial examples generated by the proposed method present superior recoverability, attack ability, and robustness on different datasets and network architectures, which ensure its effectiveness as a protection mechanism in social networks.

36.Learning Weighting Map for Bit-Depth Expansion within a Rational Range ⬇️

Bit-depth expansion (BDE) is one of the emerging technologies to display high bit-depth (HBD) image from low bit-depth (LBD) source. Existing BDE methods have no unified solution for various BDE situations, and directly learn a mapping for each pixel from LBD image to the desired value in HBD image, which may change the given high-order bits and lead to a huge deviation from the ground truth. In this paper, we design a bit restoration network (BRNet) to learn a weight for each pixel, which indicates the ratio of the replenished value within a rational range, invoking an accurate solution without modifying the given high-order bit information. To make the network adaptive for any bit-depth degradation, we investigate the issue in an optimization perspective and train the network under progressive training strategy for better performance. Moreover, we employ Wasserstein distance as a visual quality indicator to evaluate the difference of color distribution between restored image and the ground truth. Experimental results show our method can restore colorful images with fewer artifacts and false contours, and outperforms state-of-the-art methods with higher PSNR/SSIM results and lower Wasserstein distance. The source code will be made available at this https URL

37.Causal Reasoning with Spatial-temporal Representation Learning: A Prospective Study ⬇️

Spatial-temporal representation learning is ubiquitous in various real-world applications, including visual comprehension, video understanding, multi-modal analysis, human-computer interaction, and urban computing. Due to the emergence of huge amounts of multi-modal heterogeneous spatial/temporal/spatial-temporal data in big data era, the existing visual methods rely heavily on large-scale data annotations and supervised learning to learn a powerful big model. However, the lack of interpretability, robustness, and out-of-distribution generalization are becoming the bottleneck problems of these models, which hinders the progress of interpretable and reliable artificial intelligence. The majority of the existing methods are based on correlation learning with the assumption that the data are independent and identically distributed, which lack an unified guidance and analysis about why modern spatial-temporal representation learning methods have limited interpretability and easily collapse into dataset bias. Inspired by the strong inference ability of human-level agents, recent years have therefore witnessed great effort in developing causal reasoning paradigms to realize robust representation and model learning with good interpretability. In this paper, we conduct a comprehensive review of existing causal reasoning methods for spatial-temporal representation learning, covering fundamental theories, models, and datasets. The limitations of current methods and datasets are also discussed. Moreover, we propose some primary challenges, opportunities, and future research directions for benchmarking causal reasoning algorithms in spatial-temporal representation learning.

38.Contrastive learning-based computational histopathology predict differential expression of cancer driver genes ⬇️

Digital pathological analysis is run as the main examination used for cancer diagnosis. Recently, deep learning-driven feature extraction from pathology images is able to detect genetic variations and tumor environment, but few studies focus on differential gene expression in tumor cells. In this paper, we propose a self-supervised contrastive learning framework, HistCode, to infer differential gene expressions from whole slide images (WSIs). We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological feature in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes. Our extensive experiments showed that our method outperformed other state-of-the-art models in tumor diagnosis tasks, and also effectively predicted differential gene expressions. Interestingly, we found the higher fold-changed genes can be more precisely predicted. To intuitively illustrate the ability to extract informative features from pathological images, we spatially visualized the WSIs colored by the attentive scores of image tiles. We found that the tumor and necrosis areas were highly consistent with the annotations of experienced pathologists. Moreover, the spatial heatmap generated by lymphocyte-specific gene expression patterns was also consistent with the manually labeled WSI.

39.BronchoPose: an analysis of data and model configuration for vision-based bronchoscopy pose estimation ⬇️

Vision-based bronchoscopy (VB) models require the registration of the virtual lung model with the frames from the video bronchoscopy to provide effective guidance during the biopsy. The registration can be achieved by either tracking the position and orientation of the bronchoscopy camera or by calibrating its deviation from the pose (position and orientation) simulated in the virtual lung model. Recent advances in neural networks and temporal image processing have provided new opportunities for guided bronchoscopy. However, such progress has been hindered by the lack of comparative experimental conditions.
In the present paper, we share a novel synthetic dataset allowing for a fair comparison of methods. Moreover, this paper investigates several neural network architectures for the learning of temporal information at different levels of subject personalization. In order to improve orientation measurement, we also present a standardized comparison framework and a novel metric for camera orientation learning. Results on the dataset show that the proposed metric and architectures, as well as the standardized conditions, provide notable improvements to current state-of-the-art camera pose estimation in video bronchoscopy.

40.SceneTrilogy: On Scene Sketches and its Relationship with Text and Photo ⬇️

We for the first time extend multi-modal scene understanding to include that of free-hand scene sketches. This uniquely results in a trilogy of scene data modalities (sketch, text, and photo), where each offers unique perspectives for scene understanding, and together enable a series of novel scene-specific applications across discriminative (retrieval) and generative (captioning) tasks. Our key objective is to learn a common three-way embedding space that enables many-to-many modality interactions (e.g, sketch+text $\rightarrow$ photo retrieval). We importantly leverage the information bottleneck theory to achieve this goal, where we (i) decouple intra-modality information by minimising the mutual information between modality-specific and modality-agnostic components via a conditional invertible neural network, and (ii) align \textit{cross-modalities information} by maximising the mutual information between their modality-agnostic components using InfoNCE, with a specific multihead attention mechanism to allow many-to-many modality interactions. We spell out a few insights on the complementarity of each modality for scene understanding, and study for the first time a series of scene-specific applications like joint sketch- and text-based image retrieval, sketch captioning.

41.Robust Dual-Graph Regularized Moving Object Detection ⬇️

Moving object detection and its associated background-foreground separation have been widely used in a lot of applications, including computer vision, transportation and surveillance. Due to the presence of the static background, a video can be naturally decomposed into a low-rank background and a sparse foreground. Many regularization techniques, such as matrix nuclear norm, have been imposed on the background. In the meanwhile, sparsity or smoothness based regularizations, such as total variation and $\ell_1$, can be imposed on the foreground. Moreover, graph Laplacians are further imposed to capture the complicated geometry of background images. Recently, weighted regularization techniques including the weighted nuclear norm regularization have been proposed in the image processing community to promote adaptive sparsity while achieving efficient performance. In this paper, we propose a robust dual-graph regularized moving object detection model based on the weighted nuclear norm regularization, which is solved by the alternating direction method of multipliers (ADMM). Numerical experiments on body movement data sets have demonstrated the effectiveness of this method in separating moving objects from background, and the great potential in robotic applications.

42.Temporal Relevance Analysis for Video Action Models ⬇️

In this paper, we provide a deep analysis of temporal modeling for action recognition, an important but underexplored problem in the literature. We first propose a new approach to quantify the temporal relationships between frames captured by CNN-based action models based on layer-wise relevance propagation. We then conduct comprehensive experiments and in-depth analysis to provide a better understanding of how temporal modeling is affected by various factors such as dataset, network architecture, and input frames. With this, we further study some important questions for action recognition that lead to interesting findings. Our analysis shows that there is no strong correlation between temporal relevance and model performance; and action models tend to capture local temporal information, but less long-range dependencies. Our codes and models will be publicly available.

43.DArch: Dental Arch Prior-assisted 3D Tooth Instance Segmentation ⬇️

Automatic tooth instance segmentation on 3D dental models is a fundamental task for computer-aided orthodontic treatments. Existing learning-based methods rely heavily on expensive point-wise annotations. To alleviate this problem, we are the first to explore a low-cost annotation way for 3D tooth instance segmentation, i.e., labeling all tooth centroids and only a few teeth for each dental model. Regarding the challenge when only weak annotation is provided, we present a dental arch prior-assisted 3D tooth segmentation method, namely DArch. Our DArch consists of two stages, including tooth centroid detection and tooth instance segmentation. Accurately detecting the tooth centroids can help locate the individual tooth, thus benefiting the segmentation. Thus, our DArch proposes to leverage the dental arch prior to assist the detection. Specifically, we firstly propose a coarse-to-fine method to estimate the dental arch, in which the dental arch is initially generated by Bezier curve regression, and then a graph-based convolutional network (GCN) is trained to refine it. With the estimated dental arch, we then propose a novel Arch-aware Point Sampling (APS) method to assist the tooth centroid proposal generation. Meantime, a segmentor is independently trained using a patch-based training strategy, aiming to segment a tooth instance from a 3D patch centered at the tooth centroid. Experimental results on $4,773$ dental models have shown our DArch can accurately segment each tooth of a dental model, and its performance is superior to the state-of-the-art methods.

44.ProCST: Boosting Semantic Segmentation using Progressive Cyclic Style-Transfer ⬇️

Using synthetic data for training neural networks that achieve good performance on real-world data is an important task as it has the potential to reduce the need for costly data annotation. Yet, a network that is trained on synthetic data alone does not perform well on real data due to the domain gap between the two. Reducing this gap, also known as domain adaptation, has been widely studied in recent years. In the unsupervised domain adaptation (UDA) framework, unlabeled real data is used during training with labeled synthetic data to obtain a neural network that performs well on real data. In this work, we focus on image data. For the semantic segmentation task, it has been shown that performing image-to-image translation from source to target, and then training a network for segmentation on source annotations - leads to poor results. Therefore a joint training of both is essential, which has been a common practice in many techniques. Yet, closing the large domain gap between the source and the target by directly performing the adaptation between the two is challenging. In this work, we propose a novel two-stage framework for improving domain adaptation techniques. In the first step, we progressively train a multi-scale neural network to perform an initial transfer between the source data to the target data. We denote the new transformed data as "Source in Target" (SiT). Then, we use the generated SiT data as the input to any standard UDA approach. This new data has a reduced domain gap from the desired target domain, and the applied UDA approach further closes the gap. We demonstrate the improvement achieved by our framework with two state-of-the-art methods for semantic segmentation, DAFormer and ProDA, on two UDA tasks, GTA5 to Cityscapes and Synthia to Cityscapes. Code and state-of-the-art checkpoints of ProCST+DAFormer are provided.

45.Evolutionary latent space search for driving human portrait generation ⬇️

This article presents an evolutionary approach for synthetic human portraits generation based on the latent space exploration of a generative adversarial network. The idea is to produce different human face images very similar to a given target portrait. The approach applies StyleGAN2 for portrait generation and FaceNet for face similarity evaluation. The evolutionary search is based on exploring the real-coded latent space of StyleGAN2. The main results over both synthetic and real images indicate that the proposed approach generates accurate and diverse solutions, which represent realistic human portraits. The proposed research can contribute to improving the security of face recognition systems.

46.Real or Virtual: A Video Conferencing Background Manipulation-Detection System ⬇️

Recently, the popularity and wide use of the last-generation video conferencing technologies created an exponential growth in its market size. Such technology allows participants in different geographic regions to have a virtual face-to-face meeting. Additionally, it enables users to employ a virtual background to conceal their own environment due to privacy concerns or to reduce distractions, particularly in professional settings. Nevertheless, in scenarios where the users should not hide their actual locations, they may mislead other participants by claiming their virtual background as a real one. Therefore, it is crucial to develop tools and strategies to detect the authenticity of the considered virtual background. In this paper, we present a detection strategy to distinguish between real and virtual video conferencing user backgrounds. We demonstrate that our detector is robust against two attack scenarios. The first scenario considers the case where the detector is unaware about the attacks and inn the second scenario, we make the detector aware of the adversarial attacks, which we refer to Adversarial Multimedia Forensics (i.e, the forensically-edited frames are included in the training set). Given the lack of publicly available dataset of virtual and real backgrounds for video conferencing, we created our own dataset and made them publicly available [1]. Then, we demonstrate the robustness of our detector against different adversarial attacks that the adversary considers. Ultimately, our detector's performance is significant against the CRSPAM1372 [2] features, and post-processing operations such as geometric transformations with different quality factors that the attacker may choose. Moreover, our performance results shows that we can perfectly identify a real from a virtual background with an accuracy of 99.80%.

47.On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning ⬇️

Humans are able to identify and categorize novel compositions of known concepts. The task in Compositional Zero-Shot learning (CZSL) is to learn composition of primitive concepts, i.e. objects and states, in such a way that even their novel compositions can be zero-shot classified. In this work, we do not assume any prior knowledge on the feasibility of novel compositions i.e.open-world setting, where infeasible compositions dominate the search space. We propose a Compositional Variational Graph Autoencoder (CVGAE) approach for learning the variational embeddings of the primitive concepts (nodes) as well as feasibility of their compositions (via edges). Such modelling makes CVGAE scalable to real-world application scenarios. This is in contrast to SOTA method, CGE, which is computationally very expensive. e.g.for benchmark C-GQA dataset, CGE requires 3.94 x 10^5 nodes, whereas CVGAE requires only 1323 nodes. We learn a mapping of the graph and image embeddings onto a common embedding space. CVGAE adopts a deep metric learning approach and learns a similarity metric in this space via bi-directional contrastive loss between projected graph and image embeddings. We validate the effectiveness of our approach on three benchmark datasets.We also demonstrate via an image retrieval task that the representations learnt by CVGAE are better suited for compositional generalization.

48.From One Hand to Multiple Hands: Imitation Learning for Dexterous Manipulation from Single-Camera Teleoperation ⬇️

We propose to perform imitation learning for dexterous manipulation with multi-finger robot hand from human demonstrations, and transfer the policy to the real robot hand. We introduce a novel single-camera teleoperation system to collect the 3D demonstrations efficiently with only an iPad and a computer. One key contribution of our system is that we construct a customized robot hand for each user in the physical simulator, which is a manipulator resembling the same kinematics structure and shape of the operator's hand. This provides an intuitive interface and avoid unstable human-robot hand retargeting for data collection, leading to large-scale and high quality data. Once the data is collected, the customized robot hand trajectories can be converted to different specified robot hands (models that are manufactured) to generate training demonstrations. With imitation learning using our data, we show large improvement over baselines with multiple complex manipulation tasks. Importantly, we show our learned policy is significantly more robust when transferring to the real robot. More videos can be found in the this https URL .

49.Coarse-to-fine Q-attention with Tree Expansion ⬇️

Coarse-to-fine Q-attention enables sample-efficient robot manipulation by discretizing the translation space in a coarse-to-fine manner, where the resolution gradually increases at each layer in the hierarchy. Although effective, Q-attention suffers from "coarse ambiguity" - when voxelization is significantly coarse, it is not feasible to distinguish similar-looking objects without first inspecting at a finer resolution. To combat this, we propose to envision Q-attention as a tree that can be expanded and used to accumulate value estimates across the top-k voxels at each Q-attention depth. When our extension, Q-attention with Tree Expansion (QTE), replaces standard Q-attention in the Attention-driven Robot Manipulation (ARM) system, we are able to accomplish a larger set of tasks; especially on those that suffer from "coarse ambiguity". In addition to evaluating our approach across 12 RLBench tasks, we also show that the improved performance is visible in a real-world task involving small objects.

50.Meta-free representation learning for few-shot learning via stochastic weight averaging ⬇️

Recent studies on few-shot classification using transfer learning pose challenges to the effectiveness and efficiency of episodic meta-learning algorithms. Transfer learning approaches are a natural alternative, but they are restricted to few-shot classification. Moreover, little attention has been on the development of probabilistic models with well-calibrated uncertainty from few-shot samples, except for some Bayesian episodic learning algorithms. To tackle the aforementioned issues, we propose a new transfer learning method to obtain accurate and reliable models for few-shot regression and classification. The resulting method does not require episodic meta-learning and is called meta-free representation learning (MFRL). MFRL first finds low-rank representation generalizing well on meta-test tasks. Given the learned representation, probabilistic linear models are fine-tuned with few-shot samples to obtain models with well-calibrated uncertainty. The proposed method not only achieves the highest accuracy on a wide range of few-shot learning benchmark datasets but also correctly quantifies the prediction uncertainty. In addition, weight averaging and temperature scaling are effective in improving the accuracy and reliability of few-shot learning in existing meta-learning algorithms with a wide range of learning paradigms and model architectures.

51.RadioPathomics: Multimodal Learning in Non-Small Cell Lung Cancer for Adaptive Radiotherapy ⬇️

The current cancer treatment practice collects multimodal data, such as radiology images, histopathology slides, genomics and clinical data. The importance of these data sources taken individually has fostered the recent raise of radiomics and pathomics, i.e. the extraction of quantitative features from radiology and histopathology images routinely collected to predict clinical outcomes or to guide clinical decisions using artificial intelligence algorithms. Nevertheless, how to combine them into a single multimodal framework is still an open issue. In this work we therefore develop a multimodal late fusion approach that combines hand-crafted features computed from radiomics, pathomics and clinical data to predict radiation therapy treatment outcomes for non-small-cell lung cancer patients. Within this context, we investigate eight different late fusion rules (i.e. product, maximum, minimum, mean, decision template, Dempster-Shafer, majority voting, and confidence rule) and two patient-wise aggregation rules leveraging the richness of information given by computer tomography images and whole-slide scans. The experiments in leave-one-patient-out cross-validation on an in-house cohort of 33 patients show that the proposed multimodal paradigm with an AUC equal to $90.9%$ outperforms each unimodal approach, suggesting that data integration can advance precision medicine. As a further contribution, we also compare the hand-crafted representations with features automatically computed by deep networks, and the late fusion paradigm with early fusion, another popular multimodal approach. In both cases, the experiments show that the proposed multimodal approach provides the best results.

52.On Fragile Features and Batch Normalization in Adversarial Training ⬇️

Modern deep learning architecture utilize batch normalization (BN) to stabilize training and improve accuracy. It has been shown that the BN layers alone are surprisingly expressive. In the context of robustness against adversarial examples, however, BN is argued to increase vulnerability. That is, BN helps to learn fragile features. Nevertheless, BN is still used in adversarial training, which is the de-facto standard to learn robust features. In order to shed light on the role of BN in adversarial training, we investigate to what extent the expressiveness of BN can be used to robustify fragile features in comparison to random features. On CIFAR10, we find that adversarially fine-tuning just the BN layers can result in non-trivial adversarial robustness. Adversarially training only the BN layers from scratch, in contrast, is not able to convey meaningful adversarial robustness. Our results indicate that fragile features can be used to learn models with moderate adversarial robustness, while random features cannot

53.An Algorithm for the Labeling and Interactive Visualization of the Cerebrovascular System of Ischemic Strokes ⬇️

During the diagnosis of ischemic strokes, the Circle of Willis and its surrounding vessels are the arteries of interest. Their visualization in case of an acute stroke is often enabled by Computed Tomography Angiography (CTA). Still, the identification and analysis of the cerebral arteries remain time consuming in such scans due to a large number of peripheral vessels which may disturb the visual impression. In previous work we proposed VirtualDSA++, an algorithm designed to segment and label the cerebrovascular tree on CTA scans. Especially with stroke patients, labeling is a delicate procedure, as in the worst case whole hemispheres may not be present due to impeded perfusion. Hence, we extended the labeling mechanism for the cerebral arteries to identify occluded vessels. In the work at hand, we place the algorithm in a clinical context by evaluating the labeling and occlusion detection on stroke patients, where we have achieved labeling sensitivities comparable to other works between 92,% and 95,%. To the best of our knowledge, ours is the first work to address labeling and occlusion detection at once, whereby a sensitivity of 67,% and a specificity of 81,% were obtained for the latter. VirtualDSA++ also automatically segments and models the intracranial system, which we further used in a deep learning driven follow up work. We present the generic concept of iterative systematic search for pathways on all nodes of said model, which enables new interactive features. Exemplary, we derive in detail, firstly, the interactive planning of vascular interventions like the mechanical thrombectomy and secondly, the interactive suppression of vessel structures that are not of interest in diagnosing strokes (like veins). We discuss both features as well as further possibilities emerging from the proposed concept.

54.A Novel Framework for Characterization of Tumor-Immune Spatial Relationships in Tumor Microenvironment ⬇️

Understanding the impact of tumor biology on the composition of nearby cells often requires characterizing the impact of biologically distinct tumor regions. Biomarkers have been developed to label biologically distinct tumor regions, but challenges arise because of differences in the spatial extent and distribution of differentially labeled regions. In this work, we present a framework for systematically investigating the impact of distinct tumor regions on cells near the tumor borders, accounting their cross spatial distributions. We apply the framework to multiplex immunohistochemistry (mIHC) studies of pancreatic cancer and show its efficacy in demonstrating how biologically different tumor regions impact the immune response in the tumor microenvironment. Furthermore, we show that the proposed framework can be extended to largescale whole slide image analysis.

55.A Comparative Study on Approaches to Acoustic Scene Classification using CNNs ⬇️

Acoustic scene classification is a process of characterizing and classifying the environments from sound recordings. The first step is to generate features (representations) from the recorded sound and then classify the background environments. However, different kinds of representations have dramatic effects on the accuracy of the classification. In this paper, we explored the three such representations on classification accuracy using neural networks. We investigated the spectrograms, MFCCs, and embeddings representations using different CNN networks and autoencoders. Our dataset consists of sounds from three settings of indoors and outdoors environments - thus the dataset contains sound from six different kinds of environments. We found that the spectrogram representation has the highest classification accuracy while MFCC has the lowest classification accuracy. We reported our findings, insights as well as some guidelines to achieve better accuracy for environment classification using sounds.

56.Acquiring a Dynamic Light Field through a Single-Shot Coded Image ⬇️

We propose a method for compressively acquiring a dynamic light field (a 5-D volume) through a single-shot coded image (a 2-D measurement). We designed an imaging model that synchronously applies aperture coding and pixel-wise exposure coding within a single exposure time. This coding scheme enables us to effectively embed the original information into a single observed image. The observed image is then fed to a convolutional neural network (CNN) for light-field reconstruction, which is jointly trained with the camera-side coding patterns. We also developed a hardware prototype to capture a real 3-D scene moving over time. We succeeded in acquiring a dynamic light field with 5x5 viewpoints over 4 temporal sub-frames (100 views in total) from a single observed image. Repeating capture and reconstruction processes over time, we can acquire a dynamic light field at 4x the frame rate of the camera. To our knowledge, our method is the first to achieve a finer temporal resolution than the camera itself in compressive light-field acquisition. Our software is available from our project webpage

57.AAU-net: An Adaptive Attention U-net for Breast Lesions Segmentation in Ultrasound Images ⬇️

Various deep learning methods have been proposed to segment breast lesion from ultrasound images. However, similar intensity distributions, variable tumor morphology and blurred boundaries present challenges for breast lesions segmentation, especially for malignant tumors with irregular shapes. Considering the complexity of ultrasound images, we develop an adaptive attention U-net (AAU-net) to segment breast lesions automatically and stably from ultrasound images. Specifically, we introduce a hybrid adaptive attention module, which mainly consists of a channel self-attention block and a spatial self-attention block, to replace the traditional convolution operation. Compared with the conventional convolution operation, the design of the hybrid adaptive attention module can help us capture more features under different receptive fields. Different from existing attention mechanisms, the hybrid adaptive attention module can guide the network to adaptively select more robust representation in channel and space dimensions to cope with more complex breast lesions segmentation. Extensive experiments with several state-of-the-art deep learning segmentation methods on three public breast ultrasound datasets show that our method has better performance on breast lesion segmentation. Furthermore, robustness analysis and external experiments demonstrate that our proposed AAU-net has better generalization performance on the segmentation of breast lesions. Moreover, the hybrid adaptive attention module can be flexibly applied to existing network frameworks.

58.Information Fusion: Scaling Subspace-Driven Approaches ⬇️

In this work, we seek to exploit the deep structure of multi-modal data to robustly exploit the group subspace distribution of the information using the Convolutional Neural Network (CNN) formalism. Upon unfolding the set of subspaces constituting each data modality, and learning their corresponding encoders, an optimized integration of the generated inherent information is carried out to yield a characterization of various classes. Referred to as deep Multimodal Robust Group Subspace Clustering (DRoGSuRe), this approach is compared against the independently developed state-of-the-art approach named Deep Multimodal Subspace Clustering (DMSC). Experiments on different multimodal datasets show that our approach is competitive and more robust in the presence of noise.

59.Estimating the Resize Parameter in End-to-end Learned Image Compression ⬇️

We describe a search-free resizing framework that can further improve the rate-distortion tradeoff of recent learned image compression models. Our approach is simple: compose a pair of differentiable downsampling/upsampling layers that sandwich a neural compression model. To determine resize factors for different inputs, we utilize another neural network jointly trained with the compression model, with the end goal of minimizing the rate-distortion objective. Our results suggest that "compression friendly" downsampled representations can be quickly determined during encoding by using an auxiliary network and differentiable image warping. By conducting extensive experimental tests on existing deep image compression models, we show results that our new resizing parameter estimation framework can provide Bjøntegaard-Delta rate (BD-rate) improvement of about 10% against leading perceptual quality engines. We also carried out a subjective quality study, the results of which show that our new approach yields favorable compressed images. To facilitate reproducible research in this direction, the implementation used in this paper is being made freely available online at: this https URL.

60.Assessing the ability of generative adversarial networks to learn canonical medical image statistics ⬇️

In recent years, generative adversarial networks (GANs) have gained tremendous popularity for potential applications in medical imaging, such as medical image synthesis, restoration, reconstruction, translation, as well as objective image quality assessment. Despite the impressive progress in generating high-resolution, perceptually realistic images, it is not clear if modern GANs reliably learn the statistics that are meaningful to a downstream medical imaging application. In this work, the ability of a state-of-the-art GAN to learn the statistics of canonical stochastic image models (SIMs) that are relevant to objective assessment of image quality is investigated. It is shown that although the employed GAN successfully learned several basic first- and second-order statistics of the specific medical SIMs under consideration and generated images with high perceptual quality, it failed to correctly learn several per-image statistics pertinent to the these SIMs, highlighting the urgent need to assess medical image GANs in terms of objective measures of image quality.

61.Visual Acuity Prediction on Real-Life Patient Data Using a Machine Learning Based Multistage System ⬇️

In ophthalmology, intravitreal operative medication therapy (IVOM) is widespread treatment for diseases such as the age-related macular degeneration (AMD), the diabetic macular edema (DME), as well as the retinal vein occlusion (RVO). However, in real-world settings, patients often suffer from loss of vision on time scales of years despite therapy, whereas the prediction of the visual acuity (VA) and the earliest possible detection of deterioration under real-life conditions is challenging due to heterogeneous and incomplete data. In this contribution, we present a workflow for the development of a research-compatible data corpus fusing different IT systems of the department of ophthalmology of a German maximum care hospital. The extensive data corpus allows predictive statements of the expected progression of a patient and his or her VA in each of the three diseases. Within our proposed multistage system, we classify the VA progression into the three groups of therapy "winners", "stabilizers", and "losers" (WSL scheme). Our OCT biomarker classification using an ensemble of deep neural networks results in a classification accuracy (F1-score) of over 98 %, enabling us to complete incomplete OCT documentations while allowing us to exploit them for a more precise VA modelling process. Our VA prediction requires at least four VA examinations and optionally OCT biomarkers from the same time period to predict the VA progression within a forecasted time frame. While achieving a prediction accuracy of up to 69 % (macro average F1-score) when considering all three WSL-based progression groups, this corresponds to an improvement by 11 % in comparison to our ophthalmic expertise (58 %).

62.A Closer Look at Personalization in Federated Image Classification ⬇️

Federated Learning (FL) is developed to learn a single global model across the decentralized data, while is susceptible when realizing client-specific personalization in the presence of statistical heterogeneity. However, studies focus on learning a robust global model or personalized classifiers, which yield divergence due to inconsistent objectives. This paper shows that it is possible to achieve flexible personalization after the convergence of the global model by introducing representation learning. In this paper, we first analyze and determine that non-IID data harms representation learning of the global model. Existing FL methods adhere to the scheme of jointly learning representations and classifiers, where the global model is an average of classification-based local models that are consistently subject to heterogeneity from non-IID data. As a solution, we separate representation learning from classification learning in FL and propose RepPer, an independent two-stage personalized FL framework.We first learn the client-side feature representation models that are robust to non-IID data and aggregate them into a global common representation model. After that, we achieve personalization by learning a classifier head for each client, based on the common representation obtained at the former stage. Notably, the proposed two-stage learning scheme of RepPer can be potentially used for lightweight edge computing that involves devices with constrained computation power.Experiments on various datasets (CIFAR-10/100, CINIC-10) and heterogeneous data setup show that RepPer outperforms alternatives in flexibility and personalization on non-IID data.

63.Scaling Cross-Domain Content-Based Image Retrieval for E-commerce Snap and Search Application ⬇️

In this industry talk at ECIR 2022, we illustrate how we approach the main challenges from large scale cross-domain content-based image retrieval using a cascade method and a combination of our visual search and classification capabilities. Specifically, we present a system that is able to handle the scale of the data for e-commerce usage and the cross-domain nature of the query and gallery image pools. We showcase the approach applied in real-world e-commerce snap and search use case and its impact on ranking and latency performance.