1.GLA in MediaEval 2018 Emotional Impact of Movies Task ⬇️
The visual and audio information from movies can evoke a variety of emotions in viewers. Towards a better understanding of viewer impact, we present our methods for the MediaEval 2018 Emotional Impact of Movies Task to predict the expected valence and arousal continuously in movies. This task, using the LIRIS-ACCEDE dataset, enables researchers to compare different approaches for predicting viewer impact from movies. Our approach leverages image, audio, and face based features computed using pre-trained neural networks. These features were computed over time and modeled using a gated recurrent unit (GRU) based network followed by a mixture of experts model to compute multiclass predictions. We smoothed these predictions using a Butterworth filter for our final result. Our method enabled us to achieve top performance in three evaluation metrics in the MediaEval 2018 task.
2.Multi-view shape estimation of transparent containers ⬇️
The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions. In this paper, we propose a method for jointly localising container-like objects and estimating their dimensions using two wide-baseline, calibrated RGB cameras. Under the assumption of vertical circular symmetry, we estimate the dimensions of an object by sampling at different heights a set of sparse circumferences with iterative shape fitting and image re-projection to verify the sampling hypotheses in each camera using semantic segmentation masks. We evaluate the proposed method on a novel dataset of objects with different degrees of transparency and captured under different backgrounds and illumination conditions. Our method, which is based on RGB images only outperforms, in terms of localisation success and dimension estimation accuracy a deep-learning based approach that uses depth maps.
3.Multi-View Matching Network for 6D Pose Estimation ⬇️
Applications that interact with the real world such as augmented reality or robot manipulation require a good understanding of the location and pose of the surrounding objects. In this paper, we present a new approach to estimate the 6 Degree of Freedom (DoF) or 6D pose of objects from a single RGB image. Our approach can be paired with an object detection and segmentation method to estimate, refine and track the pose of the objects by matching the input image with rendered images.
4.PanDA: Panoptic Data Augmentation ⬇️
The recently proposed panoptic segmentation task presents a significant challenge of image understanding with computer vision by unifying semantic segmentation and instance segmentation tasks. In this paper we present an efficient and novel panoptic data augmentation (PanDA) method which operates exclusively in pixel space, requires no additional data or training, and is computationally cheap to implement. We retrain the original state-of-the-art UPSNet panoptic segmentation model on PanDA augmented Cityscapes dataset, and demonstrate all-round performance improvement upon the original model. We also show that PanDA is effective across scales from 10 to 30,000 images, as well as generalizable to Microsoft COCO panoptic segmentation task. Finally, the effectiveness of PanDA generated unrealistic-looking training images suggest that we should rethink about optimizing levels of image realism for efficient data augmentation.
5.Literature Review of Action Recognition in the Wild ⬇️
The literature review presented below on Action Recognition in the wild is the in-depth study of Research Papers. Action Recognition problem in the untrimmed videos is a challenging task and most of the papers have tackled this problem using hand-crafted features with shallow learning techniques and sophisticated end-to-end deep learning techniques.
6.PointRGCN: Graph Convolution Networks for 3D Vehicles Detection Refinement ⬇️
In autonomous driving pipelines, perception modules provide a visual understanding of the surrounding road scene. Among the perception tasks, vehicle detection is of paramount importance for a safe driving as it identifies the position of other agents sharing the road. In our work, we propose PointRGCN: a graph-based 3D object detection pipeline based on graph convolutional networks (GCNs) which operates exclusively on 3D LiDAR point clouds. To perform more accurate 3D object detection, we leverage a graph representation that performs proposal feature and context aggregation. We integrate residual GCNs in a two-stage 3D object detection pipeline, where 3D object proposals are refined using a novel graph representation. In particular, R-GCN is a residual GCN that classifies and regresses 3D proposals, and C-GCN is a contextual GCN that further refines proposals by sharing contextual information between multiple proposals. We integrate our refinement modules into a novel 3D detection pipeline, PointRGCN, and achieve state-of-the-art performance on the easy difficulty for the bird eye view detection task.
7.Orthogonal Convolutional Neural Networks ⬇️
The instability and feature redundancy in CNNs hinders further performance improvement. Using orthogonality as a regularizer has shown success in alleviating these issues. Previous works however only considered the kernel orthogonality in the convolution layers of CNNs, which is a necessary but not sufficient condition for orthogonal convolutions in general. We propose orthogonal convolutions as regularizations in CNNs and benchmark its effect on various tasks. We observe up to 3% gain for CIFAR100 and up to 1% gain for ImageNet classification. Our experiments also demonstrate improved performance on image retrieval, inpainting and generation, which suggests orthogonal convolution improves the feature expressiveness. Empirically, we show that the uniform spectrum and reduced feature redundancy may account for the gain in performance and robustness under adversarial attacks.
8.Document Structure Extraction for Forms using Very High Resolution Semantic Segmentation ⬇️
In this work, we look at the problem of structure extraction from document images with a specific focus on forms. Forms as a document class have not received much attention, even though they comprise a significant fraction of documents and enable several applications. Forms possess a rich, complex, hierarchical, and high-density semantic structure that poses several challenges to semantic segmentation methods. We propose a prior based deep CNN-RNN hierarchical network architecture that enables document structure extraction using very high resolution(1800 x 1000) images. We divide the document image into overlapping horizontal strips such that the network segments a strip and uses its prediction mask as prior while predicting the segmentation for the subsequent strip. We perform experiments establishing the effectiveness of our strip based network architecture through ablation methods and comparison with low-resolution variations. We introduce our new rich human-annotated forms dataset, and we show that our method significantly outperforms other segmentation baselines in extracting several hierarchical structures on this dataset. We also outperform other baselines in table detection task on the Marmot dataset. Our method is currently being used in a world-leading customer experience management software suite for automated conversion of paper and PDF forms to modern HTML based forms.
9.Towards Precise End-to-end Weakly Supervised Object Detection Network ⬇️
It is challenging for weakly supervised object detection network to precisely predict the positions of the objects, since there are no instance-level category annotations. Most existing methods tend to solve this problem by using a two-phase learning procedure, i.e., multiple instance learning detector followed by a fully supervised learning detector with bounding-box regression. Based on our observation, this procedure may lead to local minima for some object categories. In this paper, we propose to jointly train the two phases in an end-to-end manner to tackle this problem. Specifically, we design a single network with both multiple instance learning and bounding-box regression branches that share the same backbone. Meanwhile, a guided attention module using classification loss is added to the backbone for effectively extracting the implicit location information in the features. Experimental results on public datasets show that our method achieves state-of-the-art performance.
10.AdaSample: Adaptive Sampling of Hard Positives for Descriptor Learning ⬇️
Triplet loss has been widely employed in a wide range of computer vision tasks, including local descriptor learning. The effectiveness of the triplet loss heavily relies on the triplet selection, in which a common practice is to first sample intra-class patches (positives) from the dataset for batch construction and then mine in-batch negatives to form triplets. For high-informativeness triplet collection, researchers mostly focus on mining hard negatives in the second stage, while paying relatively less attention to constructing informative batches. To alleviate this issue, we propose AdaSample, an adaptive online batch sampler, in this paper. Specifically, hard positives are sampled based on their informativeness. In this way, we formulate a hardness-aware positive mining pipeline within a novel maximum loss minimization training protocol. The efficacy of the proposed method is evaluated on several standard benchmarks, where it demonstrates a significant and consistent performance gain on top of the existing strong baselines.
11.Decision Propagation Networks for Image Classification ⬇️
High-level (e.g., semantic) features encoded in the latter layers of convolutional neural networks are extensively exploited for image classification, leaving low-level (e.g., color) features in the early layers underexplored. In this paper, we propose a novel Decision Propagation Module (DPM) to make an intermediate decision that could act as category-coherent guidance extracted from early layers, and then propagate it to the latter layers. Therefore, by stacking a collection of DPMs into a classification network, the generated Decision Propagation Network is explicitly formulated as to progressively encode more discriminative features guided by the decision, and then refine the decision based on the new generated features layer by layer. Comprehensive results on four publicly available datasets validate DPM could bring significant improvements for existing classification networks with minimal additional computational cost and is superior to the state-of-the-art methods.
12.SpoC: Spoofing Camera Fingerprints ⬇️
Thanks to the fast progress in synthetic media generation, creating realistic false images has become very easy. Such images can be used to wrap rich fake news with enhanced credibility, spawning a new wave of high-impact, high-risk misinformation campaigns. Therefore, there is a fast-growing interest in reliable detectors of manipulated media. The most powerful detectors, to date, rely on the subtle traces left by any device on all images acquired by it. In particular, due to proprietary in-camera processes, like demosaicing or compression, each camera model leaves trademark traces that can be exploited for forensic analyses. The absence or distortion of such traces in the target image is a strong hint of manipulation. In this paper, we challenge such detectors to gain better insight into their vulnerabilities. This is an important study in order to build better forgery detectors able to face malicious attacks. Our proposal consists of a GAN-based approach that injects camera traces into synthetic images. Given a GANgenerated image, we insert the traces of a specific camera model into it and deceive state-of-the-art detectors into believing the image was acquired by that model. Likewise, we deceive independent detectors of synthetic GAN images into believing the image is real. Experiments prove the effectiveness of the proposed method in a wide array of conditions. Moreover, no prior information on the attacked detectors is needed, but only sample images from the target camera.
13.Grapy-ML: Graph Pyramid Mutual Learning for Cross-dataset Human Parsing ⬇️
Human parsing, or human body part semantic segmentation, has been an active research topic due to its wide potential applications. In this paper, we propose a novel GRAph PYramid Mutual Learning (Grapy-ML) method to address the cross-dataset human parsing problem, where the annotations are at different granularities. Starting from the prior knowledge of the human body hierarchical structure, we devise a graph pyramid module (GPM) by stacking three levels of graph structures from coarse granularity to fine granularity subsequently. At each level, GPM utilizes the self-attention mechanism to model the correlations between context nodes. Then, it adopts a top-down mechanism to progressively refine the hierarchical features through all the levels. GPM also enables efficient mutual learning. Specifically, the network weights of the first two levels are shared to exchange the learned coarse-granularity information across different datasets. By making use of the multi-granularity labels, Grapy-ML learns a more discriminative feature representation and achieves state-of-the-art performance, which is demonstrated by extensive experiments on the three popular benchmarks, e.g. CIHP dataset. The source code is publicly available at this https URL.
14.Residual Bi-Fusion Feature Pyramid Network for Accurate Single-shot Object Detection ⬇️
State-of-the-art (SoTA) models have improved the accuracy of object detection with a large margin via a FP (feature pyramid). FP is a top-down aggregation to collect semantically strong features to improve scale invariance in both two-stage and one-stage detectors. However, this top-down pathway cannot preserve accurate object positions due to the shift-effect of pooling. Thus, the advantage of FP to improve detection accuracy will disappear when more layers are used. The original FP lacks a bottom-up pathway to offset the lost information from lower-layer feature maps. It performs well in large-sized object detection but poor in small-sized object detection. A new structure "residual feature pyramid" is proposed in this paper. It is bidirectional to fuse both deep and shallow features towards more effective and robust detection for both small-sized and large-sized objects. Due to the "residual" nature, it can be easily trained and integrated to different backbones (even deeper or lighter) than other bi-directional methods. One important property of this residual FP is: accuracy improvement is still found even if more layers are adopted. Extensive experiments on VOC and MS COCO datasets showed the proposed method achieved the SoTA results for highly-accurate and efficient object detection..
15.Exploring Frequency Domain Interpretation of Convolutional Neural Networks ⬇️
Many existing interpretation methods of convolutional neural networks (CNNs) mainly analyze in spatial domain, yet model interpretability in frequency domain has been rarely studied. To the best of our knowledge, there is no study on the interpretation of modern CNNs from the perspective of the frequency proportion of filters. In this work, we analyze the frequency properties of filters in the first layer as it is the entrance of information and relatively more convenient for analysis. By controlling the proportion of different frequency filters in the training stage, the network classification accuracy and model robustness is evaluated and our results reveal that it has a great impact on the robustness to common corruptions. Moreover, a learnable modulation of frequency proportion with perturbation in power spectrum is proposed from the perspective of frequency domain. Experiments on CIFAR-10-C show 10.97% average robustness gains for ResNet-18 with negligible natural accuracy degradation.
16.Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking ⬇️
Multi-target multi-camera tracking (MTMCT) systems track targets across cameras. Due to the continuity of target trajectories, tracking systems usually restrict their data association within a local neighborhood. In single camera tracking, local neighborhood refers to consecutive frames; in multi-camera tracking, it refers to neighboring cameras that the target may appear successively. For similarity estimation, tracking systems often adopt appearance features learned from the re-identification (re-ID) perspective. Different from tracking, re-ID usually does not have access to the trajectory cues that can limit the search space to a local neighborhood. Due to its global matching property, the re-ID perspective requires to learn global appearance features. We argue that the mismatch between the local matching procedure in tracking and the global nature of re-ID appearance features may compromise MTMCT performance.
To fit the local matching procedure in MTMCT, in this work, we introduce locality aware appearance metric (LAAM). Specifically, we design an intra-camera metric for single camera tracking, and an inter-camera metric for multi-camera tracking. Both metrics are trained with data pairs sampled from their corresponding local neighborhoods, as opposed to global sampling in the re-ID perspective. We show that the locally learned metrics can be successfully applied on top of several globally learned re-ID features. With the proposed method, we report new state-of-the-art performance on the DukeMTMC dataset, and a substantial improvement on the CityFlow dataset.
17.Discriminative Adversarial Domain Adaptation ⬇️
Given labeled instances on a source domain and unlabeled ones on a target domain, unsupervised domain adaptation aims to learn a task classifier that can well classify target instances. Recent advances rely on domain-adversarial training of deep networks to learn domain-invariant features. However, due to an issue of mode collapse induced by the separate design of task and domain classifiers, these methods are limited in aligning the joint distributions of feature and category across domains. To overcome it, we propose a novel adversarial learning method termed Discriminative Adversarial Domain Adaptation (DADA). Based on an integrated category and domain classifier, DADA has a novel adversarial objective that encourages a mutually inhibitory relation between category and domain predictions for any input instance. We show that under practical conditions, it defines a minimax game that can promote the joint distribution alignment. Except for the traditional closed set domain adaptation, we also extend DADA for extremely challenging problem settings of partial and open set domain adaptation. Experiments show the efficacy of our proposed methods and we achieve the new state of the art for all the three settings on benchmark datasets.
18.Methods of Weighted Combination for Text Field Recognition in a Video Stream ⬇️
Due to a noticeable expansion of document recognition applicability, there is a high demand for recognition on mobile devices. A mobile camera, unlike a scanner, cannot always ensure the absence of various image distortions, therefore the task of improving the recognition precision is relevant. The advantage of mobile devices over scanners is the ability to use video stream input, which allows to get multiple images of a recognized document. Despite this, not enough attention is currently paid to the issue of combining recognition results obtained from different frames when using video stream input. In this paper we propose a weighted text string recognition results combination method and weighting criteria, and provide experimental data for verifying their validity and effectiveness. Based on the obtained results, it is concluded that the use of such weighted combination is appropriate for improving the quality of the video stream recognition result.
19.Non-Autoregressive Video Captioning with Iterative Refinement ⬇️
Existing state-of-the-art autoregressive video captioning methods (ARVC) generate captions sequentially, which leads to low inference efficiency. Moreover, the word-by-word generation process does not fit human intuition of comprehending video contents (i.e., first capturing the salient visual information and then generating well-organized descriptions), resulting in unsatisfied caption diversity. In order to press close to the human manner of comprehending video contents and writing captions, this paper proposes a non-autoregressive video captioning (NAVC) model with iterative refinement. We then further propose to exploit external auxiliary scoring information to assist the iterative refinement process, which can help the model focus on the inappropriate words more accurately. Experimental results on two mainstream benchmarks, i.e., MSVD and MSR-VTT, show that our proposed method generates more felicitous and diverse captions with a generally faster decoding speed, at the cost of up to 5% caption quality compared with the autoregressive counterpart. In particular, the proposal of using auxiliary scoring information not only improves non-autoregressive performance by a large margin, but is also beneficial for the caption diversity.
20.Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness ⬇️
We present Uncertainty-aware Cascaded Stereo Network (UCS-Net) for 3D reconstruction from multiple RGB images. Multi-view stereo (MVS) aims to reconstruct fine-grained scene geometry from multi-view images. Previous learning-based MVS methods estimate per-view depth using plane sweep volumes with a fixed depth hypothesis at each plane; this generally requires densely sampled planes for desired accuracy, and it is very hard to achieve high-resolution depth. In contrast, we propose adaptive thin volumes (ATVs); in an ATV, the depth hypothesis of each plane is spatially varying, which adapts to the uncertainties of previous per-pixel depth predictions. Our UCS-Net has three stages: the first stage processes a small standard plane sweep volume to predict low-resolution depth; two ATVs are then used in the following stages to refine the depth with higher resolution and higher accuracy. Our ATV consists of only a small number of planes; yet, it efficiently partitions local depth ranges within learned small intervals. In particular, we propose to use variance-based uncertainty estimates to adaptively construct ATVs; this differentiable process introduces reasonable and fine-grained spatial partitioning. Our multi-stage framework progressively subdivides the vast scene space with increasing depth resolution and precision, which enables scene reconstruction with high completeness and accuracy in a coarse-to-fine fashion. We demonstrate that our method achieves superior performance compared with state-of-the-art benchmarks on various challenging datasets.
21.Recovering Facial Reflectance and Geometry from Multi-view Images ⬇️
While the problem of estimating shapes and diffuse reflectances of human faces from images has been extensively studied, there is relatively less work done on recovering the specular albedo. This paper presents a lightweight solution for inferring photorealistic facial reflectance and geometry. Our system processes video streams from two views of a subject, and outputs two reflectance maps for diffuse and specular albedos, as well as a vector map of surface normals. A model-based optimization approach is used, consisting of the three stages of multi-view face model fitting, facial reflectance inference and facial geometry refinement. Our approach is based on a novel formulation built upon the 3D morphable model (3DMM) for representing 3D textured faces in conjunction with the Blinn-Phong reflection model. It has the advantage of requiring only a simple setup with two video streams, and is able to exploit the interaction between the diffuse and specular reflections across multiple views as well as time frames. As a result, the method is able to reliably recover high-fidelity facial reflectance and geometry, which facilitates various applications such as generating photorealistic facial images under new viewpoints or illumination conditions.
22.Semantic Head Enhanced Pedestrian Detection in a Crowd ⬇️
Pedestrian detection in the crowd is a challenging task because of intra-class occlusion. More prior information is needed for the detector to be robust against it. Human head area is naturally a strong cue because of its stable appearance, visibility and relative location to body. Inspired by it, we adopt an extra branch to conduct semantic head detection in parallel with traditional body branch. Instead of manually labeling the head regions, we use weak annotations inferred directly from body boxes, which is named as `semantic head'. In this way, the head detection is formulated into using a special part of labeled box to detect the corresponding part of human body, which surprisingly improves the performance and robustness to occlusion. Moreover, the head-body alignment structure is explicitly explored by introducing Alignment Loss, which functions in a self-supervised manner. Based on these, we propose the head-body alignment net (HBAN) in this work, which aims to enhance pedestrian detection by fully utilizing the human head prior. Comprehensive evaluations are conducted to demonstrate the effectiveness of HBAN on CityPersons dataset.
23.Class-Conditional Domain Adaptation on Semantic Segmentation ⬇️
Semantic segmentation is an important sub-task for many applications, but pixel-level ground truth labeling is costly and there is a tendency to overfit the training data, limiting generalization. Unsupervised domain adaptation can potentially address these problems, allowing systems trained on labelled datasets from one or more source domains (including less expensive synthetic domains) to be adapted to novel target domains. The conventional approach is to automatically align the representational distributions of source and target domains. One limitation of this approach is that it tends to disadvantage lower probability classes. We address this problem by introducing a Class-Conditional Domain Adaptation method (CCDA). It includes a class-conditional multi-scale discriminator and the class-conditional loss. This novel CCDA method encourages the network to shift the domain in a class-conditional manner, and it equalizes loss over classes. We evaluate our CCDA method on two transfer tasks and demonstrate performance comparable to state-of-the-art methods.
24.AdapNet: Adaptability Decomposing Encoder-Decoder Network for Weakly Supervised Action Recognition and Localization ⬇️
The point process is a solid framework to model sequential data, such as videos, by exploring the underlying relevance. As a challenging problem for high-level video understanding, weakly supervised action recognition and localization in untrimmed videos has attracted intensive research attention. Knowledge transfer by leveraging the publicly available trimmed videos as external guidance is a promising attempt to make up for the coarse-grained video-level annotation and improve the generalization performance. However, unconstrained knowledge transfer may bring about irrelevant noise and jeopardize the learning model. This paper proposes a novel adaptability decomposing encoder-decoder network to transfer reliable knowledge between trimmed and untrimmed videos for action recognition and localization via bidirectional point process modeling, given only video-level annotations. By decomposing the original features into domain-adaptable and domain-specific ones based on their adaptability, trimmed-untrimmed knowledge transfer can be safely confined within a more coherent subspace. An encoder-decoder based structure is carefully designed and jointly optimized to facilitate effective action classification and temporal localization. Extensive experiments are conducted on two benchmark datasets (i.e., THUMOS14 and ActivityNet1.3), and experimental results clearly corroborate the efficacy of our method.
25.LucidDream: Controlled Temporally-Consistent DeepDream on Videos ⬇️
In this work, we aim to propose a set of techniques to improve the controllability and aesthetic appeal when DeepDream, which uses a pre-trained neural network to modify images by hallucinating objects into them, is applied to videos. In particular, we demonstrate a simple modification that improves control over the class of object that DeepDream is induced to hallucinate. We also show that the flickering artifacts which frequently appear when DeepDream is applied on videos can be mitigated by the use of an additional temporal consistency loss term.
26.Can Attention Masks Improve Adversarial Robustness? ⬇️
Deep Neural Networks (DNNs) are known to be susceptible to adversarial examples. Adversarial examples are maliciously crafted inputs that are designed to fool a model, but appear normal to human beings. Recent work has shown that pixel discretization can be used to make classifiers for MNIST highly robust to adversarial examples. However, pixel discretization fails to provide significant protection on more complex datasets. In this paper, we take the first step towards reconciling these contrary findings. Focusing on the observation that discrete pixelization in MNIST makes the background completely black and foreground completely white, we hypothesize that the important property for increasing robustness is the elimination of image background using attention masks before classifying an object. To examine this hypothesis, we create foreground attention masks for two different datasets, GTSRB and MS-COCO. Our initial results suggest that using attention mask leads to improved robustness. On the adversarially trained classifiers, we see an adversarial robustness increase of over 20% on MS-COCO.
27.Transfer Learning in Visual and Relational Reasoning ⬇️
Transfer learning is becoming the de facto solution for vision and text encoders in the front-end processing of machine learning solutions. Utilizing vast amounts of knowledge in pre-trained models and subsequent fine-tuning allows achieving better performance in domains where labeled data is limited. In this paper, we analyze the efficiency of transfer learning in visual reasoning by introducing a new model (SAMNet) and testing it on two datasets: COG and CLEVR. Our new model achieves state-of-the-art accuracy on COG and shows significantly better generalization capabilities compared to the baseline. We also formalize a taxonomy of transfer learning for visual reasoning around three axes: feature, temporal, and reasoning transfer. Based on extensive experimentation of transfer learning on each of the two datasets, we show the performance of the new model along each axis.
28.CSPNet: A New Backbone that can Enhance Learning Capability of CNN ⬇️
Neural networks have enabled state-of-the-art approaches to achieve incredible results on computer vision tasks such as object detection. However, such success greatly relies on costly computation resources, which hinders people with cheap devices from appreciating the advanced technology. In this paper, we propose Cross Stage Partial Network (CSPNet) to mitigate the problem that previous works require heavy inference computations from the network architecture perspective. We attribute the problem to the duplicate gradient information within network optimization. The proposed networks respect the variability of the gradients by integrating feature maps from the beginning and the end of a network stage, which, in our experiments, reduces computations by 20% with equivalent or even superior accuracy on the ImageNet dataset, and significantly outperforms state-of-the-art approaches in terms of AP50 on the MS COCO object detection dataset. The CSPNet is easy to implement and general enough to cope with architectures based on ResNet, ResNeXt, and DenseNet. Source code is at this https URL.
29.In Perfect Shape: Certifiably Optimal 3D Shape Reconstruction from 2D Landmarks ⬇️
We study the problem of 3D shape reconstruction from 2D landmarks extracted in a single image. We adopt the 3D deformable shape model and formulate the reconstruction as a joint optimization of the camera pose and the linear shape parameters. Our first contribution is to apply Lasserre's hierarchy of convex Sums-of-Squares (SOS) relaxations to solve the shape reconstruction problem and show that the SOS relaxation of order 2 empirically solves the original non-convex problem exactly. Our second contribution is to exploit the structure of the polynomial in the objective function and find a reduced set of basis monomials for the SOS relaxation that significantly decreases the size of the resulting semidefinite program (SDP) without compromising its accuracy. These two contributions, to the best of our knowledge, lead to the first certifiably optimal solver for 3D shape reconstruction, that we name Shape*. Our third contribution is to add an outlier rejection layer to Shape* using a robust cost function and graduated non-convexity. The result is a robust reconstruction algorithm, named Shape#, that tolerates a large amount of outlier measurements. We evaluate the performance of Shape* and Shape# in both simulated and real experiments, showing that Shape* outperforms local optimization and previous convex relaxation techniques, while Shape# achieves state-of-the-art performance and is robust against 70% outliers in the FG3DCar dataset.
30.GhostNet: More Features from Cheap Operations ⬇️
Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources. The redundancy in feature maps is an important characteristic of those successful CNNs, but has rarely been investigated in neural architecture design. This paper proposes a novel Ghost module to generate more feature maps from cheap operations. Based on a set of intrinsic feature maps, we apply a series of linear transformations with cheap cost to generate many ghost feature maps that could fully reveal information underlying intrinsic features. The proposed Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks. Ghost bottlenecks are designed to stack Ghost modules, and then the lightweight GhostNet can be easily established. Experiments conducted on benchmarks demonstrate that the proposed Ghost module is an impressive alternative of convolution layers in baseline models, and our GhostNet can achieve higher recognition performance (\eg
$75.7%$ top-1 accuracy) than MobileNetV3 with similar computational cost on the ImageNet ILSVRC-2012 classification dataset. Code is available at this https URL.
31.AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks ⬇️
State-of-the-art methods in the unpaired image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data. Though the existing methods have achieved promising results, they still produce unsatisfied artifacts, being able to convert low-level information while limited in transforming high-level semantics of input images. One possible reason is that generators do not have the ability to perceive the most discriminative semantic parts between the source and target domains, thus making the generated images low quality. In this paper, we propose a new Attention-Guided Generative Adversarial Networks (AttentionGAN) for the unpaired image-to-image translation task. AttentionGAN can identify the most discriminative semantic objects and minimize changes of unwanted parts for semantic manipulation problems without using extra data and models. The attention-guided generators in AttentionGAN are able to produce attention masks via a built-in attention mechanism, and then fuse the generation output with the attention masks to obtain high-quality target images. Accordingly, we also design a novel attention-guided discriminator which only considers attended regions. Extensive experiments are conducted on several generative tasks, demonstrating that the proposed model is effective to generate sharper and more realistic images compared with existing competitive models. The source code for the proposed AttentionGAN is available at this https URL.
32.Visual Physics: Discovering Physical Laws from Videos ⬇️
In this paper, we teach a machine to discover the laws of physics from video streams. We assume no prior knowledge of physics, beyond a temporal stream of bounding boxes. The problem is very difficult because a machine must learn not only a governing equation (e.g. projectile motion) but also the existence of governing parameters (e.g. velocities). We evaluate our ability to discover physical laws on videos of elementary physical phenomena, such as projectile motion or circular motion. These elementary tasks have textbook governing equations and enable ground truth verification of our approach.
33.Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation ⬇️
Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity recognition or image captioning. Various mitigation techniques have been presented to prevent models from utilizing or learning such biases. However, there has been little systematic comparison between these techniques. We design a simple but surprisingly effective visual recognition benchmark for studying bias mitigation. Using this benchmark, we provide a thorough analysis of a wide range of techniques. We highlight the shortcomings of popular adversarial training approaches for bias mitigation, propose a simple but similarly effective alternative to the inference-time Reducing Bias Amplification method of Zhao et al., and design a domain-independent training technique that outperforms all other methods. Finally, we validate our findings on the attribute classification task in the CelebA dataset, where attribute presence is known to be correlated with the gender of people in the image, and demonstrate that the proposed technique is effective at mitigating real-world gender bias.
34.Learning to Match Templates for Unseen Instance Detection ⬇️
Detecting objects in images is a quintessential problem in computer vision. Much of the focus in the literature has been on the problem of identifying the bounding box of a particular type of objects in an image. Yet, in many contexts such as robotics and augmented reality, it is more important to find a specific object instance---a unique toy or a custom industrial part for example---rather than a generic object class. Here, applications can require a rapid shift from one object instance to another, thus requiring fast turnaround which affords little-to-no training time. In this context, we propose a method for detecting objects that are unknown at training time. Our approach frames the problem as one of learned template matching, where a network is trained to match the template of an object in an image. The template is obtained by rendering a textured 3D model of the object. At test time, we provide a novel 3D object, and the network is able to successfully detect it, even under significant occlusion. Our method offers an improvement of almost 30 mAP over the previous template matching methods on the challenging Occluded Linemod (overall mAP of 50.7). With no access to the objects at training time, our method still yields detection results that are on par with existing ones that are allowed to train on the objects. By reviving this research direction in the context of more powerful, deep feature extractors, our work sets the stage for more development in the area of unseen object instance detection.
35.ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation ⬇️
We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. Our core idea is that inconsistencies in model predictions across viewpoints provide a very reliable measure of uncertainty and encourage the model to perform well irrespective of the viewpoint under which objects are observed. To incorporate this uncertainty measure, we introduce a new viewpoint entropy formulation, which is the basis of our active learning strategy. In addition, we propose uncertainty computations on a superpixel level, which exploits inherently localized signal in the segmentation task, directly lowering the annotation costs. This combination of viewpoint entropy and the use of superpixels allows to efficiently select samples that are highly informative for improving the network. We demonstrate that our proposed active learning strategy not only yields the best-performing models for the same amount of required labeled data, but also significantly reduces labeling effort. For instance, our method achieves 95% of maximum achievable network performance using only 7%, 17%, and 24% labeled data on SceneNet-RGBD, ScanNet, and Matterport3D, respectively. On these datasets, the best state-of-the-art method achieves the same performance with 14%, 27% and 33% labeled data. Finally, we demonstrate that labeling using superpixels yields the same quality of ground-truth compared to labeling whole images, but requires 25% less time.
36.Noise Robust Generative Adversarial Networks ⬇️
Generative adversarial networks (GANs) are neural networks that learn data distributions through adversarial training. In intensive studies, recent GANs have shown promising results for reproducing training data. However, in spite of noise, they reproduce data with fidelity. As an alternative, we propose a novel family of GANs called noise-robust GANs (NR-GANs), which can learn a clean image generator even when training data are noisy. In particular, NR-GANs can solve this problem without having complete noise information (e.g., the noise distribution type, noise amount, or signal-noise relation). To achieve this, we introduce a noise generator and train it along with a clean image generator. As it is difficult to generate an image and a noise separately without constraints, we propose distribution and transformation constraints that encourage the noise generator to capture only the noise-specific components. In particular, considering such constraints under different assumptions, we devise two variants of NR-GANs for signal-independent noise and three variants of NR-GANs for signal-dependent noise. On three benchmark datasets, we demonstrate the effectiveness of NR-GANs in noise robust image generation. Furthermore, we show the applicability of NR-GANs in image denoising.
37.Fully Unsupervised Probabilistic Noise2Void ⬇️
Image denoising is the first step in many biomedical image analysis pipelines and Deep Learning (DL) based methods are currently best performing. A new category of DL methods such as Noise2Void or Noise2Self can be used fully unsupervised, requiring nothing but the noisy data. However, this comes at the price of reduced reconstruction quality. The recently proposed Probabilistic Noise2Void (PN2V) improves results, but requires an additional noise model for which calibration data needs to be acquired. Here, we present improvements to PN2V that (i) replace histogram based noise models by parametric noise models, and (ii) show how suitable noise models can be created even in the absence of calibration data. This is a major step since it actually renders PN2V fully unsupervised. We demonstrate that all proposed improvements are not only academic but indeed relevant.
38.Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models ⬇️
We introduce a new local sparse attention layer that preserves two-dimensional geometry and locality. We show that by just replacing the dense attention layer of SAGAN with our construction, we obtain very significant FID, Inception score and pure visual improvements. FID score is improved from
$18.65$ to$15.94$ on ImageNet, keeping all other parameters the same. The sparse attention patterns that we propose for our new layer are designed using a novel information theoretic criterion that uses information flow graphs. We also present a novel way to invert Generative Adversarial Networks with attention. Our method extracts from the attention layer of the discriminator a saliency map, which we use to construct a new loss function for the inversion. This allows us to visualize the newly introduced attention heads and show that they indeed capture interesting aspects of two-dimensional geometry of real images.
39.Leveraging Self-supervised Denoising for Image Segmentation ⬇️
Deep learning (DL) has arguably emerged as the method of choice for the detection and segmentation of biological structures in microscopy images. However, DL typically needs copious amounts of annotated training data that is for biomedical projects typically not available and excessively expensive to generate. Additionally, tasks become harder in the presence of noise, requiring even more high-quality training data. Hence, we propose to use denoising networks to improve the performance of other DL-based image segmentation methods. More specifically, we present ideas on how state-of-the-art self-supervised CARE networks can improve cell/nuclei segmentation in microscopy data. Using two state-of-the-art baseline methods, U-Net and StarDist, we show that our ideas consistently improve the quality of resulting segmentations, especially when only limited training data for noisy micrographs are available.
40.High- and Low-level image component decomposition using VAEs for improved reconstruction and anomaly detection ⬇️
Variational Auto-Encoders have often been used for unsupervised pretraining, feature extraction and out-of-distribution and anomaly detection in the medical field. However, VAEs often lack the ability to produce sharp images and learn high-level features. We propose to alleviate these issues by adding a new branch to conditional hierarchical VAEs. This enforces a division between higher-level and lower-level features. Despite the additional computational overhead compared to a normal VAE it results in sharper and better reconstructions and can capture the data distribution similarly well (indicated by a similar or slightly better OoD detection performance).
41.Shearlets as Feature Extractor for Semantic Edge Detection: The Model-Based and Data-Driven Realm ⬇️
Semantic edge detection has recently gained a lot of attention as an image processing task, mainly due to its wide range of real-world applications. This is based on the fact that edges in images contain most of the semantic information. Semantic edge detection involves two tasks, namely pure edge detecion and edge classification. Those are in fact fundamentally distinct in terms of the level of abstraction that each task requires, which is known as the distracted supervision paradox that limits the possible performance of a supervised model in semantic edge detection. In this work, we will present a novel hybrid method to avoid the distracted supervision paradox and achieve high-performance in semantic edge detection. Our approach is based on a combination of the model-based concept of shearlets, which provides probably optimally sparse approximations of a model-class of images, and the data-driven method of a suitably designed convolutional neural netwok. Finally, we present several applications such as tomographic reconstruction and show that our approach signifiantly outperforms former methods, thereby indicating the value of such hybrid methods for the area in biomedical imaging.
42.Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search ⬇️
Differential Architecture Search (DARTS) is now a widely disseminated weight-sharing neural architecture search method. However, there are two fundamental weaknesses remain untackled. First, we observe that the well-known aggregation of skip connections during optimization is caused by an unfair advantage in an exclusive competition. Second, there is a non-negligible incongruence when discretizing continuous architectural weights to a one-hot representation. Because of these two reasons, DARTS delivers a biased solution that might not even be suboptimal. In this paper, we present a novel approach to curing both frailties. Specifically, as unfair advantages in a pure exclusive competition easily induce a monopoly, we relax the choice of operations to be collaborative, where we let each operation have an equal opportunity to develop its strength. We thus call our method Fair DARTS. Moreover, we propose a zero-one loss to directly reduce the discretization gap. Experiments are performed on two mainstream search spaces, in which we achieve new state-of-the-art networks on ImageNet. Our code is available on this https URL.
43.Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey ⬇️
Deep Learning is a state-of-the-art technique to make inference on extensive or complex data. As a black box model due to their multilayer nonlinear structure, Deep Neural Networks are often criticized to be non-transparent and their predictions not traceable by humans. Furthermore, the models learn from artificial datasets, often with bias or contaminated discriminating content. Through their increased distribution, decision-making algorithms can contribute promoting prejudge and unfairness which is not easy to notice due to lack of transparency. Hence, scientists developed several so-called explanators or explainers which try to point out the connection between input and output to represent in a simplified way the inner structure of machine learning black boxes. In this survey we differ the mechanisms and properties of explaining systems for Deep Neural Networks for Computer Vision tasks. We give a comprehensive overview about taxonomy of related studies and compare several survey papers that deal with explainability in general. We work out the drawbacks and gaps and summarize further research ideas.
44.Adaptive Initialization Method for K-means Algorithm ⬇️
The K-means algorithm is a widely used clustering algorithm that offers simplicity and efficiency. However, the traditional K-means algorithm uses the random method to determine the initial cluster centers, which make clustering results prone to local optima and then result in worse clustering performance. Many initialization methods have been proposed, but none of them can dynamically adapt to datasets with various characteristics. In our previous research, an initialization method for K-means based on hybrid distance was proposed, and this algorithm can adapt to datasets with different characteristics. However, it has the following drawbacks: (a) When calculating density, the threshold cannot be uniquely determined, resulting in unstable results. (b) Heavily depending on adjusting the parameter, the parameter must be adjusted five times to obtain better clustering results. (c) The time complexity of the algorithm is quadratic, which is difficult to apply to large datasets. In the current paper, we proposed an adaptive initialization method for the K-means algorithm (AIMK) to improve our previous work. AIMK can not only adapt to datasets with various characteristics but also obtain better clustering results within two interactions. In addition, we then leverage random sampling in AIMK, which is named as AIMK-RS, to reduce the time complexity. AIMK-RS is easily applied to large and high-dimensional datasets. We compared AIMK and AIMK-RS with 10 different algorithms on 16 normal and six extra-large datasets. The experimental results show that AIMK and AIMK-RS outperform the current initialization methods and several well-known clustering algorithms. Furthermore, AIMK-RS can significantly reduce the complexity of applying it to extra-large datasets with high dimensions. The time complexity of AIMK-RS is O(n).
45.GRIm-RePR: Prioritising Generating Important Features for Pseudo-Rehearsal ⬇️
Pseudo-rehearsal allows neural networks to learn a sequence of tasks without forgetting how to perform in earlier tasks. Preventing forgetting is achieved by introducing a generative network which can produce data from previously seen tasks so that it can be rehearsed along side learning the new task. This has been found to be effective in both supervised and reinforcement learning. Our current work aims to further prevent forgetting by encouraging the generator to accurately generate features important for task retention. More specifically, the generator is improved by introducing a second discriminator into the Generative Adversarial Network which learns to classify between real and fake items from the intermediate activation patterns that they produce when fed through a continual learning agent. Using Atari 2600 games, we experimentally find that improving the generator can considerably reduce catastrophic forgetting compared to the standard pseudo-rehearsal methods used in deep reinforcement learning. Furthermore, we propose normalising the Q-values taught to the long-term system as we observe this substantially reduces catastrophic forgetting by minimising the interference between tasks' reward functions.
46.Graph Representation for Face Analysis in Image Collections ⬇️
Given an image collection of a social event with a huge number of pictures, it is very useful to have tools that can be used to analyze how the individuals --that are present in the collection-- interact with each other. In this paper, we propose an optimal graph representation that is based on the
connectivity' of them. The connectivity of a pair of subjects gives a score that represents howconnected' they are. It is estimated based on co-occurrence, closeness, facial expressions, and the orientation of the head when they are looking to each other. In our proposed graph, the nodes represent the subjects of the collection, and the edges correspond to their connectivities. The location of the nodes is estimated according to their connectivity (the closer the nodes, the more connected are the subjects). Finally, we developed a graphical user interface in which we can click onto the nodes (or the edges) to display the corresponding images of the collection in which the subject of the nodes (or the connected subjects) are present. We present relevant results by analyzing a wedding celebration, a sitcom video, a volleyball game and images extracted from Twitter given a hashtag. We believe that this tool can be very helpful to detect the existing social relations in an image collection.
47.Novelty Detection Via Blurring ⬇️
Conventional out-of-distribution (OOD) detection schemes based on variational autoencoder or Random Network Distillation (RND) have been observed to assign lower uncertainty to the OOD than the target distribution. In this work, we discover that such conventional novelty detection schemes are also vulnerable to the blurred images. Based on the observation, we construct a novel RND-based OOD detector, SVD-RND, that utilizes blurred images during training. Our detector is simple, efficient at test time, and outperforms baseline OOD detectors in various domains. Further results show that SVD-RND learns better target distribution representation than the baseline RND algorithm. Finally, SVD-RND combined with geometric transform achieves near-perfect detection accuracy on the CelebA dataset.
48.Data Augmentation Using Adversarial Training for Construction-Equipment Classification ⬇️
Deep learning-based construction-site image analysis has recently made great progress with regard to accuracy and speed, but it requires a large amount of data. Acquiring sufficient amount of labeled construction-image data is a prerequisite for deep learning-based construction-image recognition and requires considerable time and effort. In this paper, we propose a "data augmentation" scheme based on generative adversarial networks (GANs) for construction-equipment classification. The proposed method combines a GAN and additional "adversarial training" to stably perform "data augmentation" for construction equipment. The "data augmentation" was verified via binary classification experiments involving excavator images, and the average accuracy improvement was 4.094%. In the experiment, three image sizes (32-32-3, 64-64-3, and 128-128-3) and 120, 240, and 480 training samples were used to demonstrate the robustness of the proposed method. These results demonstrated that the proposed method can effectively and reliably generate construction-equipment images and train deep learning-based classifiers for construction equipment.
49.Potential of deep features for opinion-unaware, distortion-unaware, no-reference image quality assessment ⬇️
Image Quality Assessment algorithms predict a quality score for a pristine or distorted input image, such that it correlates with human opinion. Traditional methods required a non-distorted "reference" version of the input image to compare with, in order to predict this score. However, recent "No-reference" methods circumvent this requirement by modelling the distribution of clean image features, thereby making them more suitable for practical use. However, majority of such methods either use hand-crafted features or require training on human opinion scores (supervised learning), which are difficult to obtain and standardise. We explore the possibility of using deep features instead, particularly, the encoded (bottleneck) feature maps of a Convolutional Autoencoder neural network architecture. Also, we do not train the network on subjective scores (unsupervised learning). The primary requirements for an IQA method are monotonic increase in predicted scores with increasing degree of input image distortion, and consistent ranking of images with the same distortion type and content, but different distortion levels. Quantitative experiments using the Pearson, Kendall and Spearman correlation scores on a diverse set of images show that our proposed method meets the above requirements better than the state-of-art method (which uses hand-crafted features) for three types of distortions: blurring, noise and compression artefacts. This demonstrates the potential for future research in this relatively unexplored sub-area within IQA.
50.Artificial Intelligence for Diagnosis of Skin Cancer: Challenges and Opportunities ⬇️
Recently, there has been great interest in developing Artificial Intelligence (AI) enabled computer-aided diagnostics solutions for the diagnosis of skin cancer. With the increasing incidence of skin cancers, low awareness among a growing population, and a lack of adequate clinical expertise and services, there is an immediate need for AI systems to assist clinicians in this domain. A large number of skin lesion datasets are available publicly, and researchers have developed AI solutions, particularly deep learning algorithms, to distinguish malignant skin lesions from benign lesions in different image modalities such as dermoscopic, clinical, and histopathology images. Despite the various claims of AI systems achieving higher accuracy than dermatologists in the classification of different skin lesions, these AI systems are still in the very early stages of clinical application in terms of being ready to aid clinicians in the diagnosis of skin cancers. In this review, we discuss advancements in the digital image-based AI solutions for the diagnosis of skin cancer, along with some challenges and future opportunities to improve these AI systems to support dermatologists and enhance their ability to diagnose skin cancer.
51.Compressed MRI Reconstruction Exploiting a Rotation-Invariant Total Variation Discretization ⬇️
Inspired by the first-order method of Malitsky and Pock, we propose a novel variational framework for compressed MR image reconstruction which introduces the application of a rotation-invariant discretization of total variation functional into MR imaging while exploiting BM3D frame as a sparsifying transform. The proposed model is presented as a constrained optimization problem, however, we do not use conventional ADMM-type algorithms designed for constrained problems to obtain a solution, but rather we tailor the linesearch-equipped method of Malitsky and Pock to our model, which was originally proposed for unconstrained problems. As attested by numerical experiments, this framework significantly outperforms various state-of-the-art algorithms from variational methods to adaptive and learning approaches and in particular, it eliminates the stagnating behavior of a previous work on BM3D-MRI which compromised the solution beyond a certain iteration.
52.Multi-Object Portion Tracking in 4D Fluorescence Microscopy Imagery with Deep Feature Maps ⬇️
3D fluorescence microscopy of living organisms has increasingly become an essential and powerful tool in biomedical research and diagnosis. An exploding amount of imaging data has been collected, whereas efficient and effective computational tools to extract information from them are still lagging behind. This is largely due to the challenges in analyzing biological data. Interesting biological structures are not only small, but are often morphologically irregular and highly dynamic. Although tracking cells in live organisms has been studied for years, existing tracking methods for cells are not effective in tracking subcellular structures, such as protein complexes, which feature in continuous morphological changes including split and merge, in addition to fast migration and complex motion. In this paper, we first define the problem of multi-object portion tracking to model the protein object tracking process. A multi-object tracking method with portion matching is proposed based on 3D segmentation results. The proposed method distills deep feature maps from deep networks, then recognizes and matches object portions using an extended search. Experimental results confirm that the proposed method achieves 2.96% higher on consistent tracking accuracy and 35.48% higher on event identification accuracy than the state-of-art methods.