1.The Met Dataset: Instance-level Recognition for Artworks ⬇️
This work introduces a dataset for large-scale instance-level recognition in the domain of artworks. The proposed benchmark exhibits a number of different challenges such as large inter-class similarity, long tail distribution, and many classes. We rely on the open access collection of The Met museum to form a large training set of about 224k classes, where each class corresponds to a museum exhibit with photos taken under studio conditions. Testing is primarily performed on photos taken by museum guests depicting exhibits, which introduces a distribution shift between training and testing. Testing is additionally performed on a set of images not related to Met exhibits making the task resemble an out-of-distribution detection problem. The proposed benchmark follows the paradigm of other recent datasets for instance-level recognition on different domains to encourage research on domain independent approaches. A number of suitable approaches are evaluated to offer a testbed for future comparisons. Self-supervised and supervised contrastive learning are effectively combined to train the backbone which is used for non-parametric classification that is shown as a promising direction. Dataset webpage: this http URL
2.Skeleton-Based Action Segmentation with Multi-Stage Spatial-Temporal Graph Convolutional Neural Networks ⬇️
The ability to identify and temporally segment fine-grained actions in motion capture sequences is crucial for applications in human movement analysis. Motion capture is typically performed with optical or inertial measurement systems, which encode human movement as a time series of human joint locations and orientations or their higher-order representations. State-of-the-art action segmentation approaches use multiple stages of temporal convolutions. The main idea is to generate an initial prediction with several layers of temporal convolutions and refine these predictions over multiple stages, also with temporal convolutions. Although these approaches capture long-term temporal patterns, the initial predictions do not adequately consider the spatial hierarchy among the human joints. To address this limitation, we present multi-stage spatial-temporal graph convolutional neural networks (MS-GCN). Our framework decouples the architecture of the initial prediction generation stage from the refinement stages. Specifically, we replace the initial stage of temporal convolutions with spatial-temporal graph convolutions, which better exploit the spatial configuration of the joints and their temporal dynamics. Our framework was compared to four strong baselines on five tasks. Experimental results demonstrate that our framework achieves state-of-the-art performance.
3.Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport ⬇️
Shape matching has been a long-studied problem for the computer graphics and vision community. The objective is to predict a dense correspondence between meshes that have a certain degree of deformation. Existing methods either consider the local description of sampled points or discover correspondences based on global shape information. In this work, we investigate a hierarchical learning design, to which we incorporate local patch-level information and global shape-level structures. This flexible representation enables correspondence prediction and provides rich features for the matching stage. Finally, we propose a novel optimal transport solver by recurrently updating features on non-confident nodes to learn globally consistent correspondences between the shapes. Our results on publicly available datasets suggest robust performance in presence of severe deformations without the need for extensive training or refinement.
4.Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encoding ⬇️
Trajectory forecasting is critical for autonomous platforms to make safe planning and actions. Currently, most trajectory forecasting methods assume that object trajectories have been extracted and directly develop trajectory predictors based on the ground truth trajectories. However, this assumption does not hold in practical situations. Trajectories obtained from object detection and tracking are inevitably noisy, which could cause serious forecasting errors to predictors built on ground truth trajectories. In this paper, we propose a trajectory predictor directly based on detection results without relying on explicitly formed trajectories. Different from the traditional methods which encode the motion cue of an agent based on its clearly defined trajectory, we extract the motion information only based on the affinity cues among detection results, in which an affinity-aware state update mechanism is designed to take the uncertainty of association into account. In addition, considering that there could be multiple plausible matching candidates, we aggregate the states of them. This design relaxes the undesirable effect of noisy trajectory obtained from data association. Extensive ablation experiments validate the effectiveness of our method and its generalization ability on different detectors. Cross-comparison to other forecasting schemes further proves the superiority of our method. Code will be released upon acceptance.
5.Boosting Monocular Depth Estimation with Sparse Guided Points ⬇️
Existing monocular depth estimation shows excellent robustness in the wild, but the affine-invariant prediction requires aligning with the ground truth globally while being converted into the metric depth. In this work, we firstly propose a modified locally weighted linear regression strategy to leverage sparse ground truth and generate a flexible depth transformation to correct the coarse misalignment brought by global recovery strategy. Applying this strategy, we achieve significant improvement (more than 50% at most) over most recent state-of-the-art methods on five zero-shot datasets. Moreover, we train a robust depth estimation model with 6.3 million data and analyze the training process by decoupling the inaccuracy into coarse misalignment inaccuracy and detail missing inaccuracy. As a result, our model based on ResNet50 even outperforms the state-of-the-art DPT ViT-Large model with the help of our recovery strategy. In addition to accuracy, the consistency is also boosted for simple per-frame video depth estimation. Compared with monocular depth estimation, robust video depth estimation, and depth completion methods, our pipeline obtains state-of-the-art performance on video depth estimation without any post-processing. Experiments of 3D scene reconstruction from consistent video depth are conducted for intuitive comparison as well.
6.Concept Bottleneck Model with Additional Unsupervised Concepts ⬇️
With the increasing demands for accountability, interpretability is becoming an essential capability for real-world AI applications. However, most methods utilize post-hoc approaches rather than training the interpretable model. In this article, we propose a novel interpretable model based on the concept bottleneck model (CBM). CBM uses concept labels to train an intermediate layer as the additional visible layer. However, because the number of concept labels restricts the dimension of this layer, it is difficult to obtain high accuracy with a small number of labels. To address this issue, we integrate supervised concepts with unsupervised ones trained with self-explaining neural networks (SENNs). By seamlessly training these two types of concepts while reducing the amount of computation, we can obtain both supervised and unsupervised concepts simultaneously, even for large-sized images. We refer to the proposed model as the concept bottleneck model with additional unsupervised concepts (CBM-AUC). We experimentally confirmed that the proposed model outperformed CBM and SENN. We also visualized the saliency map of each concept and confirmed that it was consistent with the semantic meanings.
7.Characterization of Semantic Segmentation Models on Mobile Platforms for Self-Navigation in Disaster-Struck Zones ⬇️
The role of unmanned vehicles for searching and localizing the victims in disaster impacted areas such as earthquake-struck zones is getting more important. Self-navigation on an earthquake zone has a unique challenge of detecting irregularly shaped obstacles such as road cracks, debris on the streets, and water puddles. In this paper, we characterize a number of state-of-the-art FCN models on mobile embedded platforms for self-navigation at these sites containing extremely irregular obstacles. We evaluate the models in terms of accuracy, performance, and energy efficiency. We present a few optimizations for our designed vision system. Lastly, we discuss the trade-offs of these models for a couple of mobile platforms that can each perform self-navigation. To enable vehicles to safely navigate earthquake-struck zones, we compiled a new annotated image database of various earthquake impacted regions that is different than traditional road damage databases. We train our database with a number of state-of-the-art semantic segmentation models in order to identify obstacles unique to earthquake-struck zones. Based on the statistics and tradeoffs, an optimal CNN model is selected for the mobile vehicular platforms, which we apply to both low-power and extremely low-power configurations of our design. To our best knowledge, this is the first study that identifies unique challenges and discusses the accuracy, performance, and energy impact of edge-based self-navigation mobile vehicles for earthquake-struck zones. Our proposed database and trained models are publicly available.
8.DocBed: A Multi-Stage OCR Solution for Documents with Complex Layouts ⬇️
Digitization of newspapers is of interest for many reasons including preservation of history, accessibility and search ability, etc. While digitization of documents such as scientific articles and magazines is prevalent in literature, one of the main challenges for digitization of newspaper lies in its complex layout (e.g. articles spanning multiple columns, text interrupted by images) analysis, which is necessary to preserve human read-order. This work provides a major breakthrough in the digitization of newspapers on three fronts: first, releasing a dataset of 3000 fully-annotated, real-world newspaper images from 21 different U.S. states representing an extensive variety of complex layouts for document layout analysis; second, proposing layout segmentation as a precursor to existing optical character recognition (OCR) engines, where multiple state-of-the-art image segmentation models and several post-processing methods are explored for document layout segmentation; third, providing a thorough and structured evaluation protocol for isolated layout segmentation and end-to-end OCR.
9.Exploring Sub-skeleton Trajectories for Interpretable Recognition of Sign Language ⬇️
Recent advances in tracking sensors and pose estimation software enable smart systems to use trajectories of skeleton joint locations for supervised learning. We study the problem of accurately recognizing sign language words, which is key to narrowing the communication gap between hard and non-hard of hearing people.
Our method explores a geometric feature space that we call `sub-skeleton' aspects of movement. We assess similarity of feature space trajectories using natural, speed invariant distance measures, which enables clear and insightful nearest neighbor classification. The simplicity and scalability of our basic method allows for immediate application in different data domains with little to no parameter tuning.
We demonstrate the effectiveness of our basic method, and a boosted variation, with experiments on data from different application domains and tracking technologies. Surprisingly, our simple methods improve sign recognition over recent, state-of-the-art approaches.
10.PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation ⬇️
Omnidirectional 3D information is essential for a wide range of applications such as Virtual Reality, Autonomous Driving, Robotics, etc. In this paper, we propose a novel, model-agnostic, two-stage pipeline for omnidirectional monocular depth estimation. Our proposed framework PanoDepth takes one 360 image as input, produces one or more synthesized views in the first stage, and feeds the original image and the synthesized images into the subsequent stereo matching stage. In the second stage, we propose a differentiable Spherical Warping Layer to handle omnidirectional stereo geometry efficiently and effectively. By utilizing the explicit stereo-based geometric constraints in the stereo matching stage, PanoDepth can generate dense high-quality depth. We conducted extensive experiments and ablation studies to evaluate PanoDepth with both the full pipeline as well as the individual modules in each stage. Our results show that PanoDepth outperforms the state-of-the-art approaches by a large margin for 360 monocular depth estimation.
11.Multi-Resolution Factor Graph Based Stereo Correspondence Algorithm ⬇️
A dense depth-map of a scene at an arbitrary view orientation can be estimated from dense view correspondences among multiple lower-dimensional views of the scene. These low-dimensional view correspondences are dependent on the geometrical relationship among the views and the scene. Determining dense view correspondences is difficult in part due to presence of homogeneous regions in the scene and due to presence of occluded regions and illumination differences among the views. We present a new multi-resolution factor graph-based stereo matching algorithm (MR-FGS) that utilizes both intra- and inter-resolution dependencies among the views as well as among the disparity estimates. The proposed framework allows exchange of information among multiple resolutions of the correspondence problem and is useful for handling larger homogeneous regions in a scene. The MR-FGS algorithm was evaluated qualitatively and quantitatively using stereo pairs in the Middlebury stereo benchmark dataset based on commonly used performance measures. When compared to a recently developed factor graph model (FGS), the MR-FGS algorithm provided more accurate disparity estimates without requiring the commonly used post-processing procedure known as the left-right consistency check. The multi-resolution dependency constraint within the factor-graph model significantly improved contrast along depth boundaries in the MR-FGS generated disparity maps.
12.Automated processing of X-ray computed tomography images via panoptic segmentation for modeling woven composite textiles ⬇️
A new, machine learning-based approach for automatically generating 3D digital geometries of woven composite textiles is proposed to overcome the limitations of existing analytical descriptions and segmentation methods. In this approach, panoptic segmentation is leveraged to produce instance segmented semantic masks from X-ray computed tomography (CT) images. This effort represents the first deep learning based automated process for segmenting unique yarn instances in a woven composite textile. Furthermore, it improves on existing methods by providing instance-level segmentation on low contrast CT datasets. Frame-to-frame instance tracking is accomplished via an intersection-over-union (IoU) approach adopted from video panoptic segmentation for assembling a 3D geometric model. A corrective recognition algorithm is developed to improve the recognition quality (RQ). The panoptic quality (PQ) metric is adopted to provide a new universal evaluation metric for reconstructed woven composite textiles. It is found that the panoptic segmentation network generalizes well to new CT images that are similar to the training set but does not extrapolate well to CT images of differing geometry, texture, and contrast. The utility of this approach is demonstrated by capturing yarn flow directions, contact regions between individual yarns, and the spatially varying cross-sectional areas of the yarns.
13.Training Semantic Descriptors for Image-Based Localization ⬇️
Vision based solutions for the localization of vehicles have become popular recently. We employ an image retrieval based visual localization approach. The database images are kept with GPS coordinates and the location of the retrieved database image serves as an approximate position of the query image. We show that localization can be performed via descriptors solely extracted from semantically segmented images. It is reliable especially when the environment is subjected to severe illumination and seasonal changes. Our experiments reveal that the localization performance of a semantic descriptor can increase up to the level of state-of-the-art RGB image based methods.
14.Fast Online Video Super-Resolution with Deformable Attention Pyramid ⬇️
Video super-resolution (VSR) has many applications that pose strict causal, real-time, and latency constraints, including video streaming and TV. We address the VSR problem under these settings, which poses additional important challenges since information from future frames are unavailable. Importantly, designing efficient, yet effective frame alignment and fusion modules remain central problems. In this work, we propose a recurrent VSR architecture based on a deformable attention pyramid (DAP). Our DAP aligns and integrates information from the recurrent state into the current frame prediction. To circumvent the computational cost of traditional attention-based methods, we only attend to a limited number of spatial locations, which are dynamically predicted by the DAP. Comprehensive experiments and analysis of the proposed key innovations show the effectiveness of our approach. We significantly reduce processing time in comparison to state-of-the-art methods, while maintaining a high performance. We surpass state-of-the-art method EDVR-M on two standard benchmarks with a speed-up of over 3x.
15.FORML: Learning to Reweight Data for Fairness ⬇️
Deployed machine learning models are evaluated by multiple metrics beyond accuracy, such as fairness and robustness. However, such models are typically trained to minimize the average loss for a single metric, which is typically a proxy for accuracy. Training to optimize a single metric leaves these models prone to fairness violations, especially when the population of sub-groups in the training data are imbalanced. This work addresses the challenge of jointly optimizing fairness and predictive performance in the multi-class classification setting by introducing Fairness Optimized Reweighting via Meta-Learning (FORML), a training algorithm that balances fairness constraints and accuracy by jointly optimizing training sample weights and a neural network's parameters. The approach increases fairness by learning to weight each training datum's contribution to the loss according to its impact on reducing fairness violations, balancing the contributions from both over- and under-represented sub-groups. We empirically validate FORML on a range of benchmark and real-world classification datasets and show that our approach improves equality of opportunity fairness criteria over existing state-of-the-art reweighting methods by approximately 1% on image classification tasks and by approximately 5% on a face attribute prediction task. This improvement is achieved without pre-processing data or post-processing model outputs, without learning an additional weighting function, and while maintaining accuracy on the original predictive metric.
16.Weakly Supervised Nuclei Segmentation via Instance Learning ⬇️
Weakly supervised nuclei segmentation is a critical problem for pathological image analysis and greatly benefits the community due to the significant reduction of labeling cost. Adopting point annotations, previous methods mostly rely on less expressive representations for nuclei instances and thus have difficulty in handling crowded nuclei. In this paper, we propose to decouple weakly supervised semantic and instance segmentation in order to enable more effective subtask learning and to promote instance-aware representation learning. To achieve this, we design a modular deep network with two branches: a semantic proposal network and an instance encoding network, which are trained in a two-stage manner with an instance-sensitive loss. Empirical results show that our approach achieves the state-of-the-art performance on two public benchmarks of pathological images from different types of organs.
17.PARCEL: Physics-based unsupervised contrastive representation learning for parallel MR imaging ⬇️
With the successful application of deep learning in magnetic resonance imaging, parallel imaging techniques based on neural networks have attracted wide attentions. However, without high-quality fully sampled datasets for training, the performance of these methods tends to be limited. To address this issue, this paper proposes a physics based unsupervised contrastive representation learning (PARCEL) method to speed up parallel MR imaging. Specifically, PARCEL has three key ingredients to achieve direct deep learning from the undersampled k-space data. Namely, a parallel framework has been developed by learning two branches of model-based networks unrolled with the conjugate gradient algorithm; Augmented undersampled k-space data randomly drawn from the obtained k-space data are used to help the parallel network to capture the detailed information. A specially designed co-training loss is designed to guide the two networks to capture the inherent features and representations of the-to-be-reconstructed MR image. The proposed method has been evaluated on in vivo datasets and compared to five state-of-the-art methods, whose results show PARCEL is able to learn useful representations for more accurate MR reconstructions without the reliance on the fully-sampled datasets.
18.Spatial Computing and Intuitive Interaction: Bringing Mixed Reality and Robotics Together ⬇️
Spatial computing -- the ability of devices to be aware of their surroundings and to represent this digitally -- offers novel capabilities in human-robot interaction. In particular, the combination of spatial computing and egocentric sensing on mixed reality devices enables them to capture and understand human actions and translate these to actions with spatial meaning, which offers exciting new possibilities for collaboration between humans and robots. This paper presents several human-robot systems that utilize these capabilities to enable novel robot use cases: mission planning for inspection, gesture-based control, and immersive teleoperation. These works demonstrate the power of mixed reality as a tool for human-robot interaction, and the potential of spatial computing and mixed reality to drive the future of human-robot interaction.
19.Optimized Potential Initialization for Low-latency Spiking Neural Networks ⬇️
Spiking Neural Networks (SNNs) have been attached great importance due to the distinctive properties of low power consumption, biological plausibility, and adversarial robustness. The most effective way to train deep SNNs is through ANN-to-SNN conversion, which have yielded the best performance in deep network structure and large-scale datasets. However, there is a trade-off between accuracy and latency. In order to achieve high precision as original ANNs, a long simulation time is needed to match the firing rate of a spiking neuron with the activation value of an analog neuron, which impedes the practical application of SNN. In this paper, we aim to achieve high-performance converted SNNs with extremely low latency (fewer than 32 time-steps). We start by theoretically analyzing ANN-to-SNN conversion and show that scaling the thresholds does play a similar role as weight normalization. Instead of introducing constraints that facilitate ANN-to-SNN conversion at the cost of model capacity, we applied a more direct way by optimizing the initial membrane potential to reduce the conversion loss in each layer. Besides, we demonstrate that optimal initialization of membrane potentials can implement expected error-free ANN-to-SNN conversion. We evaluate our algorithm on the CIFAR-10, CIFAR-100 and ImageNet datasets and achieve state-of-the-art accuracy, using fewer time-steps. For example, we reach top-1 accuracy of 93.38% on CIFAR-10 with 16 time-steps. Moreover, our method can be applied to other ANN-SNN conversion methodologies and remarkably promote performance when the time-steps is small.
20.Generalizability of Machine Learning Models: Quantitative Evaluation of Three Methodological Pitfalls ⬇️
Despite the great potential of machine learning, the lack of generalizability has hindered the widespread adoption of these technologies in routine clinical practice. We investigate three methodological pitfalls: (1) violation of independence assumption, (2) model evaluation with an inappropriate performance indicator, and (3) batch effect and how these pitfalls could affect the generalizability of machine learning models. We implement random forest and deep convolutional neural network models using several medical imaging datasets, including head and neck CT, lung CT, chest X-Ray, and histopathological images, to quantify and illustrate the effect of these pitfalls. We develop these models with and without the pitfall and compare the performance of the resulting models in terms of accuracy, precision, recall, and F1 score. Our results showed that violation of the independence assumption could substantially affect model generalizability. More specifically, (I) applying oversampling before splitting data into train, validation and test sets; (II) performing data augmentation before splitting data; (III) distributing data points for a subject across training, validation, and test sets; and (IV) applying feature selection before splitting data led to superficial boosts in model performance. We also observed that inappropriate performance indicators could lead to erroneous conclusions. Also, batch effect could lead to developing models that lack generalizability. The aforementioned methodological pitfalls lead to machine learning models with over-optimistic performance. These errors, if made, cannot be captured using internal model evaluation, and the inaccurate predictions made by the model may lead to wrong conclusions and interpretations. Therefore, avoiding these pitfalls is a necessary condition for developing generalizable models.
21.Cyclical Pruning for Sparse Neural Networks ⬇️
Current methods for pruning neural network weights iteratively apply magnitude-based pruning on the model weights and re-train the resulting model to recover lost accuracy. In this work, we show that such strategies do not allow for the recovery of erroneously pruned weights. To enable weight recovery, we propose a simple strategy called \textit{cyclical pruning} which requires the pruning schedule to be periodic and allows for weights pruned erroneously in one cycle to recover in subsequent ones. Experimental results on both linear models and large-scale deep neural networks show that cyclical pruning outperforms existing pruning algorithms, especially at high sparsity ratios. Our approach is easy to tune and can be readily incorporated into existing pruning pipelines to boost performance.
22.Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Features ⬇️
The label noise transition matrix, denoting the transition probabilities from clean labels to noisy labels, is crucial knowledge for designing statistically robust solutions. Existing estimators for noise transition matrices, e.g., using either anchor points or clusterability, focus on computer vision tasks that are relatively easier to obtain high-quality representations. However, for other tasks with lower-quality features, the uninformative variables may obscure the useful counterpart and make anchor-point or clusterability conditions hard to satisfy. We empirically observe the failures of these approaches on a number of commonly used datasets. In this paper, to handle this issue, we propose a generally practical information-theoretic approach to down-weight the less informative parts of the lower-quality features. The salient technical challenge is to compute the relevant information-theoretical metrics using only noisy labels instead of clean ones. We prove that the celebrated
$f$ -mutual information measure can often preserve the order when calculated using noisy labels. The necessity and effectiveness of the proposed method is also demonstrated by evaluating the estimation error on a varied set of tabular data and text classification tasks with lower-quality features. Code is available at this http URL.
23.Deep Learning for Ultrasound Speed-of-Sound Reconstruction: Impacts of Training Data Diversity on Stability and Robustness ⬇️
Ultrasound b-mode imaging is a qualitative approach and diagnostic quality strongly depends on operators' training and experience. Quantitative approaches can provide information about tissue properties; therefore, can be used for identifying various tissue types, e.g., speed-of-sound in the tissue can be used as a biomarker for tissue malignancy, especially in breast imaging. Recent studies showed the possibility of speed-of-sound reconstruction using deep neural networks that are fully trained on simulated data. However, because of the ever present domain shift between simulated and measured data, the stability and performance of these models in real setups are still under debate. In this study, we investigated the impacts of training data diversity on the robustness of these networks by using multiple kinds of geometrical and natural simulated phantom structures. On the simulated data, we investigated the performance of the networks on out-of-domain echogenicity, geometries, and in the presence of noise. We further inspected the stability of employing such tissue modeling in a real data acquisition setup. We demonstrated that training the network with a joint set of datasets including both geometrical and natural tissue models improves the stability of the predicted speed-of-sound values both on simulated and measured data.