1.Block-NeRF: Scalable Large Scene Neural View Synthesis ⬇️
We present Block-NeRF, a variant of Neural Radiance Fields that can represent large-scale environments. Specifically, we demonstrate that when scaling NeRF to render city-scale scenes spanning multiple blocks, it is vital to decompose the scene into individually trained NeRFs. This decomposition decouples rendering time from scene size, enables rendering to scale to arbitrarily large environments, and allows per-block updates of the environment. We adopt several architectural changes to make NeRF robust to data captured over months under different environmental conditions. We add appearance embeddings, learned pose refinement, and controllable exposure to each individual NeRF, and introduce a procedure for aligning appearance between adjacent NeRFs so that they can be seamlessly combined. We build a grid of Block-NeRFs from 2.8 million images to create the largest neural scene representation to date, capable of rendering an entire neighborhood of San Francisco.
2.F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization ⬇️
Neural network quantization is a promising compression technique to reduce memory footprint and save energy consumption, potentially leading to real-time inference. However, there is a performance gap between quantized and full-precision models. To reduce it, existing quantization approaches require high-precision INT32 or full-precision multiplication during inference for scaling or dequantization. This introduces a noticeable cost in terms of memory, speed, and required energy. To tackle these issues, we present F8Net, a novel quantization framework consisting of only fixed-point 8-bit multiplication. To derive our method, we first discuss the advantages of fixed-point multiplication with different formats of fixed-point numbers and study the statistical behavior of the associated fixed-point numbers. Second, based on the statistical and algorithmic analysis, we apply different fixed-point formats for weights and activations of different layers. We introduce a novel algorithm to automatically determine the right format for each layer during training. Third, we analyze a previous quantization algorithm -- parameterized clipping activation (PACT) -- and reformulate it using fixed-point arithmetic. Finally, we unify the recently proposed method for quantization fine-tuning and our fixed-point approach to show the potential of our method. We verify F8Net on ImageNet for MobileNet V1/V2 and ResNet18/50. Our approach achieves comparable and better performance, when compared not only to existing quantization techniques with INT32 multiplication or floating-point arithmetic, but also to the full-precision counterparts, achieving state-of-the-art performance.
3.A Human-Centered Machine-Learning Approach for Muscle-Tendon Junction Tracking in Ultrasound Images ⬇️
Biomechanical and clinical gait research observes muscles and tendons in limbs to study their functions and behaviour. Therefore, movements of distinct anatomical landmarks, such as muscle-tendon junctions, are frequently measured. We propose a reliable and time efficient machine-learning approach to track these junctions in ultrasound videos and support clinical biomechanists in gait analysis. In order to facilitate this process, a method based on deep-learning was introduced. We gathered an extensive dataset, covering 3 functional movements, 2 muscles, collected on 123 healthy and 38 impaired subjects with 3 different ultrasound systems, and providing a total of 66864 annotated ultrasound images in our network training. Furthermore, we used data collected across independent laboratories and curated by researchers with varying levels of experience. For the evaluation of our method a diverse test-set was selected that is independently verified by four specialists. We show that our model achieves similar performance scores to the four human specialists in identifying the muscle-tendon junction position. Our method provides time-efficient tracking of muscle-tendon junctions, with prediction times of up to 0.078 seconds per frame (approx. 100 times faster than manual labeling). All our codes, trained models and test-set were made publicly available and our model is provided as a free-to-use online service on this https URL.
4.Adults as Augmentations for Children in Facial Emotion Recognition with Contrastive Learning ⬇️
Emotion recognition in children can help the early identification of, and intervention on, psychological complications that arise in stressful situations such as cancer treatment. Though deep learning models are increasingly being adopted, data scarcity is often an issue in pediatric medicine, including for facial emotion recognition in children. In this paper, we study the application of data augmentation-based contrastive learning to overcome data scarcity in facial emotion recognition for children. We explore the idea of ignoring generational gaps, by adding abundantly available adult data to pediatric data, to learn better representations. We investigate different ways by which adult facial expression images can be used alongside those of children. In particular, we propose to explicitly incorporate within each mini-batch adult images as augmentations for children's. Out of
$84$ combinations of learning approaches and training set sizes, we find that supervised contrastive learning with the proposed training scheme performs best, reaching a test accuracy that typically surpasses the one of the second-best approach by 2% to 3%. Our results indicate that adult data can be considered to be a meaningful augmentation of pediatric data for the recognition of emotional facial expression in children, and open up the possibility for other applications of contrastive learning to improve pediatric care by complementing data of children with that of adults.
5.Feature-level augmentation to improve robustness of deep neural networks to affine transformations ⬇️
Recent studies revealed that convolutional neural networks do not generalize well to small image transformations, e.g. rotations by a few degrees or translations of a few pixels. To improve the robustness to such transformations, we propose to introduce data augmentation at intermediate layers of the neural architecture, in addition to the common data augmentation applied on the input images. By introducing small perturbations to activation maps (features) at various levels, we develop the capacity of the neural network to cope with such transformations. We conduct experiments on three image classification benchmarks (Tiny ImageNet, Caltech-256 and Food-101), considering two different convolutional architectures (ResNet-18 and DenseNet-121). When compared with two state-of-the-art methods, the empirical results show that our approach consistently attains the best trade-off between accuracy and mean flip rate.
6.Exploiting Spatial Sparsity for Event Cameras with Visual Transformers ⬇️
Event cameras report local changes of brightness through an asynchronous stream of output events. Events are spatially sparse at pixel locations with little brightness variation. We propose using a visual transformer (ViT) architecture to leverage its ability to process a variable-length input. The input to the ViT consists of events that are accumulated into time bins and spatially separated into non-overlapping sub-regions called patches. Patches are selected when the number of nonzero pixel locations within a sub-region is above a threshold. We show that by fine-tuning a ViT model on the selected active patches, we can reduce the average number of patches fed into the backbone during the inference by at least 50% with only a minor drop (0.34%) of the classification accuracy on the N-Caltech101 dataset. This reduction translates into a decrease of 51% in Multiply-Accumulate (MAC) operations and an increase of 46% in the inference speed using a server CPU.
7.NÜWA-LIP: Language Guided Image Inpainting with Defect-free VQGAN ⬇️
Language guided image inpainting aims to fill in the defective regions of an image under the guidance of text while keeping non-defective regions unchanged. However, the encoding process of existing models suffers from either receptive spreading of defective regions or information loss of non-defective regions, giving rise to visually unappealing inpainting results. To address the above issues, this paper proposes NÜWA-LIP by incorporating defect-free VQGAN (DF-VQGAN) with multi-perspective sequence to sequence (MP-S2S). In particular, DF-VQGAN introduces relative estimation to control receptive spreading and adopts symmetrical connections to protect information. MP-S2S further enhances visual information from complementary perspectives, including both low-level pixels and high-level tokens. Experiments show that DF-VQGAN performs more robustness than VQGAN. To evaluate the inpainting performance of our model, we built up 3 open-domain benchmarks, where NÜWA-LIP is also superior to recent strong baselines.
8.Towards Assessing and Characterizing the Semantic Robustness of Face Recognition ⬇️
Deep Neural Networks (DNNs) lack robustness against imperceptible perturbations to their input. Face Recognition Models (FRMs) based on DNNs inherit this vulnerability. We propose a methodology for assessing and characterizing the robustness of FRMs against semantic perturbations to their input. Our methodology causes FRMs to malfunction by designing adversarial attacks that search for identity-preserving modifications to faces. In particular, given a face, our attacks find identity-preserving variants of the face such that an FRM fails to recognize the images belonging to the same identity. We model these identity-preserving semantic modifications via direction- and magnitude-constrained perturbations in the latent space of StyleGAN. We further propose to characterize the semantic robustness of an FRM by statistically describing the perturbations that induce the FRM to malfunction. Finally, we combine our methodology with a certification technique, thus providing (i) theoretical guarantees on the performance of an FRM, and (ii) a formal description of how an FRM may model the notion of face identity.
9.Real-Time Siamese Multiple Object Tracker with Enhanced Proposals ⬇️
Maintaining the identity of multiple objects in real-time video is a challenging task, as it is not always possible to run a detector on every frame. Thus, motion estimation systems are often employed, which either do not scale well with the number of targets or produce features with limited semantic information. To solve the aforementioned problems and allow the tracking of dozens of arbitrary objects in real-time, we propose SiamMOTION. SiamMOTION includes a novel proposal engine that produces quality features through an attention mechanism and a region-of-interest extractor fed by an inertia module and powered by a feature pyramid network. Finally, the extracted tensors enter a comparison head that efficiently matches pairs of exemplars and search areas, generating quality predictions via a pairwise depthwise region proposal network and a multi-object penalization module. SiamMOTION has been validated on five public benchmarks, achieving leading performance against current state-of-the-art trackers.
10.OWL (Observe, Watch, Listen): Localizing Actions in Egocentric Video via Audiovisual Temporal Context ⬇️
Temporal action localization (TAL) is an important task extensively explored and improved for third-person videos in recent years. Recent efforts have been made to perform fine-grained temporal localization on first-person videos. However, current TAL methods only use visual signals, neglecting the audio modality that exists in most videos and that shows meaningful action information in egocentric videos. In this work, we take a deep look into the effectiveness of audio in detecting actions in egocentric videos and introduce a simple-yet-effective approach via Observing, Watching, and Listening (OWL) to leverage audio-visual information and context for egocentric TAL. For doing that, we: 1) compare and study different strategies for where and how to fuse the two modalities; 2) propose a transformer-based model to incorporate temporal audio-visual context. Our experiments show that our approach achieves state-of-the-art performance on EPIC-KITCHENS-100.
11.Spherical Transformer ⬇️
Using convolutional neural networks for 360images can induce sub-optimal performance due to distortions entailed by a planar projection. The distortion gets deteriorated when a rotation is applied to the 360image. Thus, many researches based on convolutions attempt to reduce the distortions to learn accurate representation. In contrast, we leverage the transformer architecture to solve image classification problems for 360images. Using the proposed transformer for 360images has two advantages. First, our method does not require the erroneous planar projection process by sampling pixels from the sphere surface. Second, our sampling method based on regular polyhedrons makes low rotation equivariance errors, because specific rotations can be reduced to permutations of faces. In experiments, we validate our network on two aspects, as follows. First, we show that using a transformer with highly uniform sampling methods can help reduce the distortion. Second, we demonstrate that the transformer architecture can achieve rotation equivariance on specific rotations. We compare our method to other state-of-the-art algorithms using the SPH-MNIST, SPH-CIFAR, and SUN360 datasets and show that our method is competitive with other methods.
12.FILM: Frame Interpolation for Large Motion ⬇️
We present a frame interpolation algorithm that synthesizes multiple intermediate frames from two input images with large in-between motion. Recent methods use multiple networks to estimate optical flow or depth and a separate network dedicated to frame synthesis. This is often complex and requires scarce optical flow or depth ground-truth. In this work, we present a single unified network, distinguished by a multi-scale feature extractor that shares weights at all scales, and is trainable from frames alone. To synthesize crisp and pleasing frames, we propose to optimize our network with the Gram matrix loss that measures the correlation difference between feature maps. Our approach outperforms state-of-the-art methods on the Xiph large motion benchmark. We also achieve higher scores on Vimeo-90K, Middlebury and UCF101, when comparing to methods that use perceptual losses. We study the effect of weight sharing and of training with datasets of increasing motion range. Finally, we demonstrate our model's effectiveness in synthesizing high quality and temporally coherent videos on a challenging near-duplicate photos dataset. Codes and pre-trained models are available at this https URL.
13.Towards the automated large-scale reconstruction of past road networks from historical maps ⬇️
Transportation infrastructure, such as road or railroad networks, represent a fundamental component of our civilization. For sustainable planning and informed decision making, a thorough understanding of the long-term evolution of transportation infrastructure such as road networks is crucial. However, spatially explicit, multi-temporal road network data covering large spatial extents are scarce and rarely available prior to the 2000s. Herein, we propose a framework that employs increasingly available scanned and georeferenced historical map series to reconstruct past road networks, by integrating abundant, contemporary road network data and color information extracted from historical maps. Specifically, our method uses contemporary road segments as analytical units and extracts historical roads by inferring their existence in historical map series based on image processing and clustering techniques. We tested our method on over 300,000 road segments representing more than 50,000 km of the road network in the United States, extending across three study areas that cover 53 historical topographic map sheets dated between 1890 and 1950. We evaluated our approach by comparison to other historical datasets and against manually created reference data, achieving F-1 scores of up to 0.95, and showed that the extracted road network statistics are highly plausible over time, i.e., following general growth patterns. We demonstrated that contemporary geospatial data integrated with information extracted from historical map series open up new avenues for the quantitative analysis of long-term urbanization processes and landscape changes far beyond the era of operational remote sensing and digital cartography.
14.PVSeRF: Joint Pixel-, Voxel- and Surface-Aligned Radiance Field for Single-Image Novel View Synthesis ⬇️
We present PVSeRF, a learning framework that reconstructs neural radiance fields from single-view RGB images, for novel view synthesis. Previous solutions, such as pixelNeRF, rely only on pixel-aligned features and suffer from feature ambiguity issues. As a result, they struggle with the disentanglement of geometry and appearance, leading to implausible geometries and blurry results. To address this challenge, we propose to incorporate explicit geometry reasoning and combine it with pixel-aligned features for radiance field prediction. Specifically, in addition to pixel-aligned features, we further constrain the radiance field learning to be conditioned on i) voxel-aligned features learned from a coarse volumetric grid and ii) fine surface-aligned features extracted from a regressed point cloud. We show that the introduction of such geometry-aware features helps to achieve a better disentanglement between appearance and geometry, i.e. recovering more accurate geometries and synthesizing higher quality images of novel views. Extensive experiments against state-of-the-art methods on ShapeNet benchmarks demonstrate the superiority of our approach for single-image novel view synthesis.
15.Consistency and Diversity induced Human Motion Segmentation ⬇️
Subspace clustering is a classical technique that has been widely used for human motion segmentation and other related tasks. However, existing segmentation methods often cluster data without guidance from prior knowledge, resulting in unsatisfactory segmentation results. To this end, we propose a novel Consistency and Diversity induced human Motion Segmentation (CDMS) algorithm. Specifically, our model factorizes the source and target data into distinct multi-layer feature spaces, in which transfer subspace learning is conducted on different layers to capture multi-level information. A multi-mutual consistency learning strategy is carried out to reduce the domain gap between the source and target data. In this way, the domain-specific knowledge and domain-invariant properties can be explored simultaneously. Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance. Moreover, to preserve the temporal correlations, an enhanced graph regularizer is imposed on the learned representation coefficients and the multi-level representations of the source data. The proposed model can be efficiently solved using the Alternating Direction Method of Multipliers (ADMM) algorithm. Extensive experimental results on public human motion datasets demonstrate the effectiveness of our method against several state-of-the-art approaches.
16.Geometric Digital Twinning of Industrial Facilities: Retrieval of Industrial Shapes ⬇️
This paper devises, implements and benchmarks a novel shape retrieval method that can accurately match individual labelled point clusters (instances) of existing industrial facilities with their respective CAD models. It employs a combination of image and point cloud deep learning networks to classify and match instances to their geometrically similar CAD model. It extends our previous research on geometric digital twin generation from point cloud data, which currently is a tedious, manual process. Experiments with our joint network reveal that it can reliably retrieve CAD models at 85.2% accuracy. The proposed research is a fundamental framework to enable the geometric Digital Twin (gDT) pipeline and incorporate the real geometric configuration into the Digital Twin.
17.Bias-Eliminated Semantic Refinement for Any-Shot Learning ⬇️
When training samples are scarce, the semantic embedding technique, ie, describing class labels with attributes, provides a condition to generate visual features for unseen objects by transferring the knowledge from seen objects. However, semantic descriptions are usually obtained in an external paradigm, such as manual annotation, resulting in weak consistency between descriptions and visual features. In this paper, we refine the coarse-grained semantic description for any-shot learning tasks, ie, zero-shot learning (ZSL), generalized zero-shot learning (GZSL), and few-shot learning (FSL). A new model, namely, the semantic refinement Wasserstein generative adversarial network (SRWGAN) model, is designed with the proposed multihead representation and hierarchical alignment techniques. Unlike conventional methods, semantic refinement is performed with the aim of identifying a bias-eliminated condition for disjoint-class feature generation and is applicable in both inductive and transductive settings. We extensively evaluate model performance on six benchmark datasets and observe state-of-the-art results for any-shot learning; eg, we obtain 70.2% harmonic accuracy for the Caltech UCSD Birds (CUB) dataset and 82.2% harmonic accuracy for the Oxford Flowers (FLO) dataset in the standard GZSL setting. Various visualizations are also provided to show the bias-eliminated generation of SRWGAN. Our code is available.
18.Weakly-Supervised Semantic Segmentation with Visual Words Learning and Hybrid Pooling ⬇️
Weakly-Supervised Semantic Segmentation (WSSS) methods with image-level labels generally train a classification network to generate the Class Activation Maps (CAMs) as the initial coarse segmentation labels. However, current WSSS methods still perform far from satisfactorily because their adopted CAMs 1) typically focus on partial discriminative object regions and 2) usually contain useless background regions. These two problems are attributed to the sole image-level supervision and aggregation of global information when training the classification networks. In this work, we propose the visual words learning module and hybrid pooling approach, and incorporate them in the classification network to mitigate the above problems. In the visual words learning module, we counter the first problem by enforcing the classification network to learn fine-grained visual word labels so that more object extents could be discovered. Specifically, the visual words are learned with a codebook, which could be updated via two proposed strategies, i.e. learning-based strategy and memory-bank strategy. The second drawback of CAMs is alleviated with the proposed hybrid pooling, which incorporates the global average and local discriminative information to simultaneously ensure object completeness and reduce background regions. We evaluated our methods on PASCAL VOC 2012 and MS COCO 2014 datasets. Without any extra saliency prior, our method achieved 70.6% and 70.7% mIoU on the
$val$ and$test$ set of PASCAL VOC dataset, respectively, and 36.2% mIoU on the$val$ set of MS COCO dataset, which significantly surpassed the performance of state-of-the-art WSSS methods.
19.The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning ⬇️
Humans have remarkable capacity to reason abductively and hypothesize about what lies beyond the literal content of an image. By identifying concrete visual clues scattered throughout a scene, we almost can't help but draw probable inferences beyond the literal scene based on our everyday experience and knowledge about the world. For example, if we see a "20 mph" sign alongside a road, we might assume the street sits in a residential area (rather than on a highway), even if no houses are pictured. Can machines perform similar visual reasoning?
We present Sherlock, an annotated corpus of 103K images for testing machine capacity for abductive reasoning beyond literal image contents. We adopt a free-viewing paradigm: participants first observe and identify salient clues within images (e.g., objects, actions) and then provide a plausible inference about the scene, given the clue. In total, we collect 363K (clue, inference) pairs, which form a first-of-its-kind abductive visual reasoning dataset. Using our corpus, we test three complementary axes of abductive reasoning. We evaluate the capacity of models to: i) retrieve relevant inferences from a large candidate corpus; ii) localize evidence for inferences via bounding boxes, and iii) compare plausible inferences to match human judgments on a newly-collected diagnostic corpus of 19K Likert-scale judgments. While we find that fine-tuning CLIP-RN50x64 with a multitask objective outperforms strong baselines, significant headroom exists between model performance and human agreement. We provide analysis that points towards future work.
20.Adversarial Attack and Defense of YOLO Detectors in Autonomous Driving Scenarios ⬇️
Visual detection is a key task in autonomous driving, and it serves as one foundation for self-driving planning and control. Deep neural networks have achieved promising results in various computer vision tasks, but they are known to be vulnerable to adversarial attacks. A comprehensive understanding of deep visual detectors' vulnerability is required before people can improve their robustness. However, only a few adversarial attack/defense works have focused on object detection, and most of them employed only classification and/or localization losses, ignoring the objectness aspect. In this paper, we identify a serious objectness-related adversarial vulnerability in YOLO detectors and present an effective attack strategy aiming the objectness aspect of visual detection in autonomous vehicles. Furthermore, to address such vulnerability, we propose a new objectness-aware adversarial training approach for visual detection. Experiments show that the proposed attack targeting the objectness aspect is 45.17% and 43.50% more effective than those generated from classification and/or localization losses on the KITTI and COCO_traffic datasets, respectively. Also, the proposed adversarial defense approach can improve the detectors' robustness against objectness-oriented attacks by up to 21% and 12% mAP on KITTI and COCO_traffic, respectively.
21.Sampling Strategy for Fine-Tuning Segmentation Models to Crisis Area under Scarcity of Data ⬇️
The use of remote sensing in humanitarian crisis response missions is well-established and has proven relevant repeatedly. One of the problems is obtaining gold annotations as it is costly and time consuming which makes it almost impossible to fine-tune models to new regions affected by the crisis. Where time is critical, resources are limited and environment is constantly changing, models has to evolve and provide flexible ways to adapt to a new situation. The question that we want to answer is if prioritization of samples provide better results in fine-tuning vs other classical sampling methods under annotated data scarcity? We propose a method to guide data collection during fine-tuning, based on estimated model and sample properties, like predicted IOU score. We propose two formulas for calculating sample priority. Our approach blends techniques from interpretability, representation learning and active learning. We have applied our method to a deep learning model for semantic segmentation, U-Net, in a remote sensing application of building detection - one of the core use cases of remote sensing in humanitarian applications. Preliminary results shows utility in prioritization of samples for tuning semantic segmentation models under scarcity of data condition.
22.A Novel Encoder-Decoder Network with Guided Transmission Map for Single Image Dehazing ⬇️
A novel Encoder-Decoder Network with Guided Transmission Map (EDN-GTM) for single image dehazing scheme is proposed in this paper. The proposed EDN-GTM takes conventional RGB hazy image in conjunction with its transmission map estimated by adopting dark channel prior as the inputs of the network. The proposed EDN-GTM utilizes U-Net for image segmentation as the core network and utilizes various modifications including spatial pyramid pooling module and Swish activation to achieve state-of-the-art dehazing performance. Experiments on benchmark datasets show that the proposed EDN-GTM outperforms most of traditional and deep learning-based image dehazing schemes in terms of PSNR and SSIM metrics. The proposed EDN-GTM furthermore proves its applicability to object detection problems. Specifically, when applied to an image preprocessing tool for driving object detection, the proposed EDN-GTM can efficiently remove haze and significantly improve detection accuracy by 4.73% in terms of mAP measure. The code is available at: this https URL.
23.DeepSSN: a deep convolutional neural network to assess spatial scene similarity ⬇️
Spatial-query-by-sketch is an intuitive tool to explore human spatial knowledge about geographic environments and to support communication with scene database queries. However, traditional sketch-based spatial search methods perform insufficiently due to their inability to find hidden multi-scale map features from mental sketches. In this research, we propose a deep convolutional neural network, namely Deep Spatial Scene Network (DeepSSN), to better assess the spatial scene similarity. In DeepSSN, a triplet loss function is designed as a comprehensive distance metric to support the similarity assessment. A positive and negative example mining strategy using qualitative constraint networks in spatial reasoning is designed to ensure a consistently increasing distinction of triplets during the training process. Moreover, we develop a prototype spatial scene search system using the proposed DeepSSN, in which the users input spatial query via sketch maps and the system can automatically augment the sketch training data. The proposed model is validated using multi-source conflated map data including 131,300 labeled scene samples after data augmentation. The empirical results demonstrate that the DeepSSN outperforms baseline methods including k-nearest-neighbors, multilayer perceptron, AlexNet, DenseNet, and ResNet using mean reciprocal rank and precision metrics. This research advances geographic information retrieval studies by introducing a novel deep learning method tailored to spatial scene queries.
24.Estimation of Clinical Workload and Patient Activity using Deep Learning and Optical Flow ⬇️
Contactless monitoring using thermal imaging has become increasingly proposed to monitor patient deterioration in hospital, most recently to detect fevers and infections during the COVID-19 pandemic. In this letter, we propose a novel method to estimate patient motion and observe clinical workload using a similar technical setup but combined with open source object detection algorithms (YOLOv4) and optical flow. Patient motion estimation was used to approximate patient agitation and sedation, while worker motion was used as a surrogate for caregiver workload. Performance was illustrated by comparing over 32000 frames from videos of patients recorded in an Intensive Care Unit, to clinical agitation scores recorded by clinical workers.
25.Graph Neural Network for Cell Tracking in Microscopy Videos ⬇️
We present a novel graph neural network (GNN) approach for cell tracking in high-throughput microscopy videos. By modeling the entire time-lapse sequence as a direct graph where cell instances are represented by its nodes and their associations by its edges, we extract the entire set of cell trajectories by looking for the maximal paths in the graph. This is accomplished by several key contributions incorporated into an end-to-end deep learning framework. We exploit a deep metric learning algorithm to extract cell feature vectors that distinguish between instances of different biological cells and assemble same cell instances. We introduce a new GNN block type which enables a mutual update of node and edge feature vectors, thus facilitating the underlying message passing process. The message passing concept, whose extent is determined by the number of GNN blocks, is of fundamental importance as it enables the `flow' of information between nodes and edges much behind their neighbors in consecutive frames. Finally, we solve an edge classification problem and use the identified active edges to construct the cells' tracks and lineage trees. We demonstrate the strengths of the proposed cell tracking approach by applying it to 2D and 3D datasets of different cell types, imaging setups, and experimental conditions. We show that our framework outperforms most of the current state-of-the-art methods.
26.PINs: Progressive Implicit Networks for Multi-Scale Neural Representations ⬇️
Multi-layer perceptrons (MLP) have proven to be effective scene encoders when combined with higher-dimensional projections of the input, commonly referred to as \textit{positional encoding}. However, scenes with a wide frequency spectrum remain a challenge: choosing high frequencies for positional encoding introduces noise in low structure areas, while low frequencies result in poor fitting of detailed regions. To address this, we propose a progressive positional encoding, exposing a hierarchical MLP structure to incremental sets of frequency encodings. Our model accurately reconstructs scenes with wide frequency bands and learns a scene representation at progressive level of detail \textit{without explicit per-level supervision}. The architecture is modular: each level encodes a continuous implicit representation that can be leveraged separately for its respective resolution, meaning a smaller network for coarser reconstructions. Experiments on several 2D and 3D datasets show improvements in reconstruction accuracy, representational capacity and training speed compared to baselines.
27.A Joint Variational Multichannel Multiphase Segmentation Framework ⬇️
In this paper, we propose a variational image segmentation framework for multichannel multiphase image segmentation based on the Chan-Vese active contour model. The core of our method lies in finding a variable u encoding the segmentation, by minimizing a multichannel energy functional that combines the information of multiple images. We create a decomposition of the input, either by multichannel filtering, or simply by using plain natural RGB, or medical images, which already consist of several channels. Subsequently we minimize the proposed functional for each of the channels simultaneously. Our model meets the necessary assumptions such that it can be solved efficiently by optimization techniques like the Chambolle-Pock method. We prove that the proposed energy functional has global minimizers, and show its stability and convergence with respect to noisy inputs. Experimental results show that the proposed method performs well in single- and multichannel segmentation tasks, and can be employed to the segmentation of various types of images, such as natural and texture images as well as medical images.
28.Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging ⬇️
Image-to-image regression is an important learning task, used frequently in biological imaging. Current algorithms, however, do not generally offer statistical guarantees that protect against a model's mistakes and hallucinations. To address this, we develop uncertainty quantification techniques with rigorous statistical guarantees for image-to-image regression problems. In particular, we show how to derive uncertainty intervals around each pixel that are guaranteed to contain the true value with a user-specified confidence probability. Our methods work in conjunction with any base machine learning model, such as a neural network, and endow it with formal mathematical guarantees -- regardless of the true unknown data distribution or choice of model. Furthermore, they are simple to implement and computationally inexpensive. We evaluate our procedure on three image-to-image regression tasks: quantitative phase microscopy, accelerated magnetic resonance imaging, and super-resolution transmission electron microscopy of a Drosophila melanogaster brain.
29.Towards Predicting Fine Finger Motions from Ultrasound Images via Kinematic Representation ⬇️
A central challenge in building robotic prostheses is the creation of a sensor-based system able to read physiological signals from the lower limb and instruct a robotic hand to perform various tasks. Existing systems typically perform discrete gestures such as pointing or grasping, by employing electromyography (EMG) or ultrasound (US) technologies to analyze the state of the muscles. In this work, we study the inference problem of identifying the activation of specific fingers from a sequence of US images when performing dexterous tasks such as keyboard typing or playing the piano. While estimating finger gestures has been done in the past by detecting prominent gestures, we are interested in classification done in the context of fine motions that evolve over time. We consider this task as an important step towards higher adoption rates of robotic prostheses among arm amputees, as it has the potential to dramatically increase functionality in performing daily tasks. Our key observation, motivating this work, is that modeling the hand as a robotic manipulator allows to encode an intermediate representation wherein US images are mapped to said configurations. Given a sequence of such learned configurations, coupled with a neural-network architecture that exploits temporal coherence, we are able to infer fine finger motions. We evaluated our method by collecting data from a group of subjects and demonstrating how our framework can be used to replay music played or text typed. To the best of our knowledge, this is the first study demonstrating these downstream tasks within an end-to-end system.
30.Visual Servoing for Pose Control of Soft Continuum Arm in a Structured Environment ⬇️
For soft continuum arms, visual servoing is a popular control strategy that relies on visual feedback to close the control loop. However, robust visual servoing is challenging as it requires reliable feature extraction from the image, accurate control models and sensors to perceive the shape of the arm, both of which can be hard to implement in a soft robot. This letter circumvents these challenges by presenting a deep neural network-based method to perform smooth and robust 3D positioning tasks on a soft arm by visual servoing using a camera mounted at the distal end of the arm. A convolutional neural network is trained to predict the actuations required to achieve the desired pose in a structured environment. Integrated and modular approaches for estimating the actuations from the image are proposed and are experimentally compared. A proportional control law is implemented to reduce the error between the desired and current image as seen by the camera. The model together with the proportional feedback control makes the described approach robust to several variations such as new targets, lighting, loads, and diminution of the soft arm. Furthermore, the model lends itself to be transferred to a new environment with minimal effort.
31.Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity Estimation ⬇️
Endoscopic Mayo score and Ulcerative Colitis Endoscopic Index of Severity are commonly used scoring systems for the assessment of endoscopic severity of ulcerative colitis. They are based on assigning a score in relation to the disease activity, which creates a rank among the levels, making it an ordinal regression problem. On the other hand, most studies use categorical cross-entropy loss function, which is not optimal for the ordinal regression problem, to train the deep learning models. In this study, we propose a novel loss function called class distance weighted cross-entropy (CDW-CE) that respects the order of the classes and takes the distance of the classes into account in calculation of cost. Experimental evaluations show that CDW-CE outperforms the conventional categorical cross-entropy and CORN framework, which is designed for the ordinal regression problems. In addition, CDW-CE does not require any modifications at the output layer and is compatible with the class activation map visualization techniques.
32.Deep Learning for Computational Cytology: A Survey ⬇️
Computational cytology is a critical, rapid-developing, yet challenging topic in the field of medical image computing which analyzes the digitized cytology image by computer-aided technologies for cancer screening. Recently, an increasing number of deep learning (DL) algorithms have made significant progress in medical image analysis, leading to the boosting publications of cytological studies. To investigate the advanced methods and comprehensive applications, we survey more than 120 publications of DL-based cytology image analysis in this article. We first introduce various deep learning methods, including fully supervised, weakly supervised, unsupervised, and transfer learning. Then, we systematically summarize the public datasets, evaluation metrics, versatile cytology image analysis applications including classification, detection, segmentation, and other related tasks. Finally, we discuss current challenges and potential research directions of computational cytology.
33.Equivariance Regularization for Image Reconstruction ⬇️
In this work, we propose Regularization-by-Equivariance (REV), a novel structure-adaptive regularization scheme for solving imaging inverse problems under incomplete measurements. Our regularization scheme utilizes the equivariant structure in the physics of the measurements -- which is prevalent in many inverse problems such as tomographic image reconstruction -- to mitigate the ill-poseness of the inverse problem. Our proposed scheme can be applied in a plug-and-play manner alongside with any classic first-order optimization algorithm such as the accelerated gradient descent/FISTA for simplicity and fast convergence. Our numerical experiments in sparse-view X-ray CT image reconstruction tasks demonstrate the effectiveness of our approach.
34.Monotonically Convergent Regularization by Denoising ⬇️
Regularization by denoising (RED) is a widely-used framework for solving inverse problems by leveraging image denoisers as image priors. Recent work has reported the state-of-the-art performance of RED in a number of imaging applications using pre-trained deep neural nets as denoisers. Despite the recent progress, the stable convergence of RED algorithms remains an open problem. The existing RED theory only guarantees stability for convex data-fidelity terms and nonexpansive denoisers. This work addresses this issue by developing a new monotone RED (MRED) algorithm, whose convergence does not require nonexpansiveness of the deep denoising prior. Simulations on image deblurring and compressive sensing recovery from random matrices show the stability of MRED even when the traditional RED algorithm diverges.
35.Improving performance of aircraft detection in satellite imagery while limiting the labelling effort: Hybrid active learning ⬇️
The earth observation industry provides satellite imagery with high spatial resolution and short revisit time. To allow efficient operational employment of these images, automating certain tasks has become necessary. In the defense domain, aircraft detection on satellite imagery is a valuable tool for analysts. Obtaining high performance detectors on such a task can only be achieved by leveraging deep learning and thus us-ing a large amount of labeled data. To obtain labels of a high enough quality, the knowledge of military experts is needed.We propose a hybrid clustering active learning method to select the most relevant data to label, thus limiting the amount of data required and further improving the performances. It combines diversity- and uncertainty-based active learning selection methods. For aircraft detection by segmentation, we show that this method can provide better or competitive results compared to other active learning methods.
36.Memory-based gaze prediction in deep imitation learning for robot manipulation ⬇️
Deep imitation learning is a promising approach that does not require hard-coded control rules in autonomous robot manipulation. The current applications of deep imitation learning to robot manipulation have been limited to reactive control based on the states at the current time step. However, future robots will also be required to solve tasks utilizing their memory obtained by experience in complicated environments (e.g., when the robot is asked to find a previously used object on a shelf). In such a situation, simple deep imitation learning may fail because of distractions caused by complicated environments. We propose that gaze prediction from sequential visual input enables the robot to perform a manipulation task that requires memory. The proposed algorithm uses a Transformer-based self-attention architecture for the gaze estimation based on sequential data to implement memory. The proposed method was evaluated with a real robot multi-object manipulation task that requires memory of the previous states.
37.Decreasing Annotation Burden of Pairwise Comparisons with Human-in-the-Loop Sorting: Application in Medical Image Artifact Rating ⬇️
Ranking by pairwise comparisons has shown improved reliability over ordinal classification. However, as the annotations of pairwise comparisons scale quadratically, this becomes less practical when the dataset is large. We propose a method for reducing the number of pairwise comparisons required to rank by a quantitative metric, demonstrating the effectiveness of the approach in ranking medical images by image quality in this proof of concept study. Using the medical image annotation software that we developed, we actively subsample pairwise comparisons using a sorting algorithm with a human rater in the loop. We find that this method substantially reduces the number of comparisons required for a full ordinal ranking without compromising inter-rater reliability when compared to pairwise comparisons without sorting.
38.Multiclass histogram-based thresholding using kernel density estimation and scale-space representations ⬇️
We present a new method for multiclass thresholding of a histogram which is based on the nonparametric Kernel Density (KD) estimation, where the unknown parameters of the KD estimate are defined using the Expectation-Maximization (EM) iterations. The method compares the number of extracted minima of the KD estimate with the number of the requested clusters minus one. If these numbers match, the algorithm returns positions of the minima as the threshold values, otherwise, the method gradually decreases/increases the kernel bandwidth until the numbers match. We verify the method using synthetic histograms with known threshold values and using the histogram of real X-ray computed tomography images. After thresholding of the real histogram, we estimated the porosity of the sample and compare it with the direct experimental measurements. The comparison shows the meaningfulness of the thresholding.
39.Wireless Transmission of Images With The Assistance of Multi-level Semantic Information ⬇️
Semantic-oriented communication has been considered as a promising to boost the bandwidth efficiency by only transmitting the semantics of the data. In this paper, we propose a multi-level semantic aware communication system for wireless image transmission, named MLSC-image, which is based on the deep learning techniques and trained in an end to end manner. In particular, the proposed model includes a multilevel semantic feature extractor, that extracts both the highlevel semantic information, such as the text semantics and the segmentation semantics, and the low-level semantic information, such as local spatial details of the images. We employ a pretrained image caption to capture the text semantics and a pretrained image segmentation model to obtain the segmentation semantics. These high-level and low-level semantic features are then combined and encoded by a joint semantic and channel encoder into symbols to transmit over the physical channel. The numerical results validate the effectiveness and efficiency of the proposed semantic communication system, especially under the limited bandwidth condition, which indicates the advantages of the high-level semantics in the compression of images.
40.Discovering Concepts in Learned Representations using Statistical Inference and Interactive Visualization ⬇️
Concept discovery is one of the open problems in the interpretability literature that is important for bridging the gap between non-deep learning experts and model end-users. Among current formulations, concepts defines them by as a direction in a learned representation space. This definition makes it possible to evaluate whether a particular concept significantly influences classification decisions for classes of interest. However, finding relevant concepts is tedious, as representation spaces are high-dimensional and hard to navigate. Current approaches include hand-crafting concept datasets and then converting them to latent space directions; alternatively, the process can be automated by clustering the latent space. In this study, we offer another two approaches to guide user discovery of meaningful concepts, one based on multiple hypothesis testing, and another on interactive visualization. We explore the potential value and limitations of these approaches through simulation experiments and an demo visual interface to real data. Overall, we find that these techniques offer a promising strategy for discovering relevant concepts in settings where users do not have predefined descriptions of them, but without completely automating the process.
41.Can Humans Do Less-Than-One-Shot Learning? ⬇️
Being able to learn from small amounts of data is a key characteristic of human intelligence, but exactly {\em how} small? In this paper, we introduce a novel experimental paradigm that allows us to examine classification in an extremely data-scarce setting, asking whether humans can learn more categories than they have exemplars (i.e., can humans do "less-than-one shot" learning?). An experiment conducted using this paradigm reveals that people are capable of learning in such settings, and provides several insights into underlying mechanisms. First, people can accurately infer and represent high-dimensional feature spaces from very little data. Second, having inferred the relevant spaces, people use a form of prototype-based categorization (as opposed to exemplar-based) to make categorical inferences. Finally, systematic, machine-learnable patterns in responses indicate that people may have efficient inductive biases for dealing with this class of data-scarce problems.
42.Semantic Segmentation of Anaemic RBCs Using Multilevel Deep Convolutional Encoder-Decoder Network ⬇️
Pixel-level analysis of blood images plays a pivotal role in diagnosing blood-related diseases, especially Anaemia. These analyses mainly rely on an accurate diagnosis of morphological deformities like shape, size, and precise pixel counting. In traditional segmentation approaches, instance or object-based approaches have been adopted that are not feasible for pixel-level analysis. The convolutional neural network (CNN) model required a large dataset with detailed pixel-level information for the semantic segmentation of red blood cells in the deep learning domain. In current research work, we address these problems by proposing a multi-level deep convolutional encoder-decoder network along with two state-of-the-art healthy and Anaemic-RBC datasets. The proposed multi-level CNN model preserved pixel-level semantic information extracted in one layer and then passed to the next layer to choose relevant features. This phenomenon helps to precise pixel-level counting of healthy and anaemic-RBC elements along with morphological analysis. For experimental purposes, we proposed two state-of-the-art RBC datasets, i.e., Healthy-RBCs and Anaemic-RBCs dataset. Each dataset contains 1000 images, ground truth masks, relevant, complete blood count (CBC), and morphology reports for performance evaluation. The proposed model results were evaluated using crossmatch analysis with ground truth mask by finding IoU, individual training, validation, testing accuracies, and global accuracies using a 05-fold training procedure. This model got training, validation, and testing accuracies as 0.9856, 0.9760, and 0.9720 on the Healthy-RBC dataset and 0.9736, 0.9696, and 0.9591 on an Anaemic-RBC dataset. The IoU and BFScore of the proposed model were 0.9311, 0.9138, and 0.9032, 0.8978 on healthy and anaemic datasets, respectively.
43.Multi-modal unsupervised brain image registration using edge maps ⬇️
Diffeomorphic deformable multi-modal image registration is a challenging task which aims to bring images acquired by different modalities to the same coordinate space and at the same time to preserve the topology and the invertibility of the transformation. Recent research has focused on leveraging deep learning approaches for this task as these have been shown to achieve competitive registration accuracy while being computationally more efficient than traditional iterative registration methods. In this work, we propose a simple yet effective unsupervised deep learning-based {\em multi-modal} image registration approach that benefits from auxiliary information coming from the gradient magnitude of the image, i.e. the image edges, during the training. The intuition behind this is that image locations with a strong gradient are assumed to denote a transition of tissues, which are locations of high information value able to act as a geometry constraint. The task is similar to using segmentation maps to drive the training, but the edge maps are easier and faster to acquire and do not require annotations. We evaluate our approach in the context of registering multi-modal (T1w to T2w) magnetic resonance (MR) brain images of different subjects using three different loss functions that are said to assist multi-modal registration, showing that in all cases the auxiliary information leads to better results without compromising the runtime.
44.FCM-DNN: diagnosing coronary artery disease by deep accuracy Fuzzy C-Means clustering model ⬇️
Cardiovascular disease is one of the most challenging diseases in middle-aged and older people, which causes high mortality. Coronary artery disease (CAD) is known as a common cardiovascular disease. A standard clinical tool for diagnosing CAD is angiography. The main challenges are dangerous side effects and high angiography costs. Today, the development of artificial intelligence-based methods is a valuable achievement for diagnosing disease. Hence, in this paper, artificial intelligence methods such as neural network (NN), deep neural network (DNN), and Fuzzy C-Means clustering combined with deep neural network (FCM-DNN) are developed for diagnosing CAD on a cardiac magnetic resonance imaging (CMRI) dataset. The original dataset is used in two different approaches. First, the labeled dataset is applied to the NN and DNN to create the NN and DNN models. Second, the labels are removed, and the unlabeled dataset is clustered via the FCM method, and then, the clustered dataset is fed to the DNN to create the FCM-DNN model. By utilizing the second clustering and modeling, the training process is improved, and consequently, the accuracy is increased. As a result, the proposed FCM-DNN model achieves the best performance with a 99.91% accuracy specifying 10 clusters, i.e., 5 clusters for healthy subjects and 5 clusters for sick subjects, through the 10-fold cross-validation technique compared to the NN and DNN models reaching the accuracies of 92.18% and 99.63%, respectively. To the best of our knowledge, no study has been conducted for CAD diagnosis on the CMRI dataset using artificial intelligence methods. The results confirm that the proposed FCM-DNN model can be helpful for scientific and research centers.