CVPR 2020 Papers

We address the problem of anomaly detection, that is, detecting anomalous events in a video sequence. Anomaly detection methods based on convolutional neural networks (CNNs) typically leverage proxy tasks, such as reconstructing input video frames, to learn models describing normality without seeing anomalous samples at training time, and quantify the extent of abnormalities using the reconstruction error at test time. The main drawbacks of these approaches are that they do not consider the diversity of normal patterns explicitly, and the powerful representation capacity of CNNs allows to reconstruct abnormal video frames. To address this problem, we present an unsupervised learning approach to anomaly detection that considers the diversity of normal patterns explicitly, while lessening the representation capacity of CNNs. To this end, we propose to use a memory module with a new update scheme where items in the memory record prototypical patterns of normal data. We also present novel feature compactness and separateness losses to train the memory, boosting the discriminative power of both memory items and deeply learned features from normal data. Experimental results on standard benchmarks demonstrate the effectiveness and efficiency of our approach, which outperforms the state of the art.

Person Re-Identification (ReID) aims to recognize a person-of-interest across different places and times. Existing ReID methods rely on images or videos collected using RGB cameras. They extract appearance features like clothes, shoes, hair, etc. Such features, however, can change drastically from one day to the next, leading to inability to identify people over extended time periods. In this paper, we introduce RF-ReID, a novel approach that harnesses radio frequency (RF) signals for longterm person ReID. RF signals traverse clothes and reflect off the human body; thus they can be used to extract more persistent human-identifying features like body size and shape. We evaluate the performance of RF-ReID on longitudinal datasets that span days and weeks, where the person may wear different clothes across days. Our experiments demonstrate that RF-ReID outperforms state-of-the-art RGB-based ReID approaches for long term person ReID. Our results also reveal two interesting features: First since RF signals work in the presence of occlusions and poor lighting, RF-ReID allows for person ReID in such scenarios. Second, unlike photos and videos which reveal personal and private information, RF signals are more privacy-preserving, and hence can help extend person ReID to privacy-concerned domains, like healthcare.

Recently, cross domain transfer has been applied for unsupervised image restoration tasks. However, directly applying existing frameworks would lead to domain-shift problems in translated images due to lack of effective supervision. Instead, we propose an unsupervised learning method that explicitly learns invariant presentation from noisy data and reconstructs clear observations. To do so, we introduce discrete disentangling representation and adversarial domain adaption into general domain transfer framework, aided by extra self-supervised modules including background and semantic consistency constraints, learning robust representation under dual domain constraints, such as feature and image domains. Experiments on synthetic and real noise removal tasks show the proposed method achieves comparable performance with other stateof-the-art supervised and unsupervised methods, while having faster and stable convergence than other domain adaption methods.

Interactions between people are often governed by their relationships. On the flip side, social relationships are built upon several interactions. Two strangers are more likely to greet and introduce themselves while becoming friends over time. We are fascinated by this interplay between interactions and relationships, and believe that it is an important aspect of understanding social situations. In this work, we propose neural models to learn and jointly predict interactions, relationships, and the pair of characters that are involved. We note that interactions are informed by a mixture of visual and dialog cues, and present a multimodal architecture to extract meaningful information from them. Localizing the pair of interacting characters in video is a time-consuming process, instead, we train our model to learn from clip-level weak labels. We evaluate our models on the MovieGraphs dataset and show the impact of modalities, use of longer temporal context for predicting relationships, and achieve encouraging performance using weak labels as compared with ground-truth labels. Code is online.

Image-level weakly-supervised semantic segmentation (WSSS) aims at learning semantic segmentation by adopting only image class labels. Existing approaches generally rely on class activation maps (CAM) to generate pseudo-masks and then train segmentation models. The main difficulty is that the CAM estimate only covers partial foreground objects. In this paper, we argue that the critical factor preventing to obtain the full object mask is the classification boundary mismatch problem in applying the CAM to WSSS. Because the CAM is optimized by the classification task, it focuses on the discrimination across different image-level classes. However, the WSSS requires to distinguish pixels sharing the same image-level class to separate them into the foreground and the background. To alleviate this contradiction, we propose an efficient end-to-end Intra-Class Discriminator (ICD) framework, which learns intra-class boundaries to help separate the foreground and the background within each image-level class. Without bells and whistles, our approach achieves the state-of-the-art performance of image label based WSSS, with mIoU 68.0% on the VOC 2012 semantic segmentation benchmark, demonstrating the effectiveness of the proposed approach.

Panoptic segmentation requires segments of both "things" (countable object instances) and "stuff" (uncountable and amorphous regions) within a single output. A common approach involves the fusion of instance segmentation (for "things") and semantic segmentation (for "stuff") into a non-overlapping placement of segments, and resolves overlaps. However, instance ordering with detection confidence do not correlate well with natural occlusion relationship. To resolve this issue, we propose a branch that is tasked with modeling how two instance masks should overlap one another as a binary relation. Our method, named OCFusion, is lightweight but particularly effective in the instance fusion process. OCFusion is trained with the ground truth relation derived automatically from the existing dataset annotations. We obtain state-of-the-art results on COCO and show competitive results on the Cityscapes panoptic segmentation benchmark.

Humans involuntarily tend to infer parts of the conversation from lip movements when the speech is absent or corrupted by external noise. In this work, we explore the task of lip to speech synthesis, i.e., learning to generate natural speech given only the lip movements of a speaker. Acknowledging the importance of contextual and speaker-specific cues for accurate lip-reading, we take a different path from existing works. We focus on learning accurate lip sequences to speech mappings for individual speakers in unconstrained, large vocabulary settings. To this end, we collect and release a large-scale benchmark dataset, the first of its kind, specifically to train and evaluate the single-speaker lip to speech task in natural settings. We propose a novel approach with key design choices to achieve accurate, natural lip to speech synthesis in such unconstrained scenarios for the first time. Extensive evaluation using quantitative, qualitative metrics and human evaluation shows that our method is four times more intelligible than previous works in this space.

Human face reenactment aims at transferring motion patterns from one face (from a source-domain video) to an-other (in the target domain with the identity of interest).While recent works report impressive results, they are notable to handle multiple identities in a unified model. In this paper, we propose a unique network of CrossID-GAN to perform multi-ID face reenactment. Given a source-domain video with extracted facial landmarks and a target-domain image, our CrossID-GAN learns the identity-invariant motion patterns via the extracted landmarks and such information to produce the videos whose ID matches that of the target domain. Both supervised and unsupervised settings are proposed to train and guide our model during training.Our qualitative/quantitative results confirm the robustness and effectiveness of our model, with ablation studies confirming our network design.

Understanding interactions between humans and objects is one of the fundamental problems in visual classification and an essential step towards detailed scene understanding. Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them. Most existing HOI detection approaches are instance-centric where interactions between all possible human-object pairs are predicted based on appearance features and coarse spatial information. We argue that appearance features alone are insufficient to capture complex human-object interactions. In this paper, we therefore propose a novel fully-convolutional approach that directly detects the interactions between human-object pairs. Our network predicts interaction points, which directly localize and classify the inter-action. Paired with the densely predicted interaction vectors, the interactions are associated with human and object detections to obtain final predictions. To the best of our knowledge, we are the first to propose an approach where HOI detection is posed as a keypoint detection and grouping problem. Experiments are performed on two popular benchmarks: V-COCO and HICO-DET. Our approach sets a new state-of-the-art on both datasets. Code is available at https://github.com/vaesl/IP-Net.

An object's geocentric pose, defined as the height above ground and orientation with respect to gravity, is a powerful representation of real-world structure for object detection, segmentation, and localization tasks using RGBD images. For close-range vision tasks, height and orientation have been derived directly from stereo-computed depth and more recently from monocular depth predicted by deep networks. For long-range vision tasks such as Earth observation, depth cannot be reliably estimated with monocular images. Inspired by recent work in monocular height above ground prediction and optical flow prediction from static images, we develop an encoding of geocentric pose to address this challenge and train a deep network to compute the representation densely, supervised by publicly available airborne lidar. We exploit these attributes to rectify oblique images and remove observed object parallax to dramatically improve the accuracy of localization and to enable accurate alignment of multiple images taken from very different oblique viewpoints. We demonstrate the value of our approach by extending two large-scale public datasets for semantic segmentation in oblique satellite images. All of our data and code are publicly available.

We present a generative model to synthesize 3D shapes as sets of handles -- lightweight proxies that approximate the original 3D shape -- for applications in interactive editing, shape parsing, and building compact 3D representations. Our model can generate handle sets with varying cardinality and different types of handles. Key to our approach is a deep architecture that predicts both the parameters and existence of shape handles and a novel similarity measure that can easily accommodate different types of handles, such as cuboids or sphere-meshes. We leverage the recent advances in semantic 3D annotation as well as automatic shape summarization techniques to supervise our approach. We show that the resulting shape representations are not only intuitive, but achieve superior quality than previous state-of-the-art. Finally, we demonstrate how our method can be used in applications such as interactive shape editing and completion, leveraging the latent space learned by our model to guide these tasks.

In this paper, we present a learning-based framework for light field view synthesis from a subset of input views. Building upon a light-weight optical flow estimation network to obtain depth maps, our method employs two reconstruction modules in pixel and feature domains respectively. For the pixel-wise reconstruction, occlusions are explicitly handled by a disparity-dependent interpolation filter, whereas inpainting on disoccluded areas is learned by convolutional layers. Due to disparity inconsistencies, the pixel-based reconstruction may lead to blurriness in highly textured areas as well as on object contours. On the contrary, the feature-based reconstruction well performs on high frequencies, making the reconstruction in the two domains complementary. End-to-end learning is finally performed including a fusion module merging pixel and feature-based reconstructions. Experimental results show that our method achieves state-of-the-art performance on both synthetic and real-world datasets, moreover, it is even able to extend light fields' baseline by extrapolating high quality views without additional training.

Learning from web data has attracted lots of research interest in recent years. However, crawled web images usually have two types of noises, label noise and background noise, which induce extra difficulties in utilizing them effectively. Most existing methods either rely on human supervision or ignore the background noise. In this paper, we propose a novel method, which is capable of handling these two types of noises together, without the supervision of clean images in the training stage. Particularly, we formulate our method under the framework of multi-instance learning by grouping ROIs (i.e., images and their region proposals) from the same category into bags. ROIs in each bag are assigned with different weights based on the representative/discriminative scores of their nearest clusters, in which the clusters and their scores are obtained via our designed memory module. Our memory module could be naturally integrated with the classification module, leading to an end-to-end trainable system. Extensive experiments on four benchmark datasets demonstrate the effectiveness of our method.

Despite great success in human parsing, progress for parsing other deformable articulated objects, like animals, is still limited by the lack of labeled data. In this paper, we use synthetic images and ground truth generated from CAD animal models to address this challenge. To bridge the domain gap between real and synthetic images, we propose a novel consistency-constrained semi-supervised learning method (CC-SSL). Our method leverages both spatial and temporal consistencies, to bootstrap weak models trained on synthetic data with unlabeled real images. We demonstrate the effectiveness of our method on highly deformable animals, such as horses and tigers. Without using any real image label, our method allows for accurate keypoint prediction on real images. Moreover, we quantitatively show that models using synthetic data achieve better generalization performance than models trained on real images across different domains in the Visual Domain Adaptation Challenge dataset. Our synthetic dataset contains 10+ animals with diverse poses and rich ground truth, which enables us to use the multi-task learning strategy to further boost models' performance.

State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding ground-truth objects. Such a harsh split conditioned on IoU results in binary labels that are potentially noisy and challenging for training. In this paper, we propose to mitigate noise incurred by imperfect label assignment such that the contributions of anchors are dynamically determined by a carefully constructed cleanliness score associated with each anchor. Exploring outputs from both regression and classification branches, the cleanliness scores, estimated without incurring any additional computational overhead, are used not only as soft labels to supervise the training of the classification branch but also sample re-weighting factors for improved localization and classification accuracy. We conduct extensive experiments on COCO, and demonstrate, among other things, the proposed approach steadily improves RetinaNet by 2% with various backbones.

Based on a combined data set of 4000 high resolution facial scans, we introduce a non-linear morphable face model, capable of producing multifarious face geometry of pore-level resolution, coupled with material attributes for use in physically-based rendering. We aim to maximize the variety of the participant's face identities, while increasing the robustness of correspondence between unique components, including middle-frequency geometry, albedo maps, specular intensity maps and high-frequency displacement details. Our deep learning based generative model learns to correlate albedo and geometry, which ensures the anatomical correctness of the generated assets. We demonstrate potential use of our generative model for novel identity generation, model fitting, interpolation, animation, high fidelity data visualization, and low-to-high resolution data domain transferring. We hope the release of this generative model will encourage further cooperation between all graphics, vision, and data focused professionals, while demonstrating the cumulative value of every individual's complete biometric profile.

Filter pruning has been widely applied to neural network compression and acceleration. Existing methods usually utilize pre-defined pruning criteria, such as Lp-norm, to prune unimportant filters. There are two major limitations to these methods. First, existing methods fail to consider the variety of filter distribution across layers. To extract features of the coarse level to the fine level, the filters of different layers have various distributions. Therefore, it is not suitable to utilize the same pruning criteria to different functional layers. Second, prevailing layer-by-layer pruning methods process each layer independently and sequentially, failing to consider that all the layers in the network collaboratively make the final prediction. In this paper, we propose Learning Filter Pruning Criteria (LFPC) to solve the above problems. Specifically, we develop a differentiable pruning criteria sampler. This sampler is learnable and optimized by the validation loss of the pruned network obtained from the sampled criteria. In this way, we could adaptively select the appropriate pruning criteria for different functional layers. Besides, when evaluating the sampled criteria, LFPC comprehensively consider the contribution of all the layers at the same time. Experiments validate our approach on three image classification benchmarks. Notably, on ILSVRC-2012, our LFPC reduces more than 60% FLOPs on ResNet-50 with only 0.83% top-5 accuracy loss.

Video object segmentation (VOS) is a highly challenging problem since the initial mask, defining the target object, is only given at test-time. The main difficulty is to effectively handle appearance changes and similar background objects, while maintaining accurate segmentation. Most previous approaches fine-tune segmentation networks on the first frame, resulting in impractical frame-rates and risk of overfitting. More recent methods integrate generative target appearance models, but either achieve limited robustness or require large amounts of training data. We propose a novel VOS architecture consisting of two network components. The target appearance model consists of a light-weight module, which is learned during the inference stage using fast optimization techniques to predict a coarse but robust target segmentation. The segmentation model is exclusively trained offline, designed to process the coarse scores into high quality segmentation masks. Our method is fast, easily trainable and remains highly effective in cases of limited training data. We perform extensive experiments on the challenging YouTube-VOS and DAVIS datasets. Our network achieves favorable performance, while operating at higher frame-rates compared to state-of-the-art. Code and trained models are available at https://github.com/andr345/frtm-vos.

Recovering sharp video sequence from a motion-blurred image is highly ill-posed due to the significant loss of motion information in the blurring process. For event-based cameras, however, fast motion can be captured as events at high frame rate, raising new opportunities to exploring effective solutions. In this paper, we start from a sequential formulation of event-based motion deblurring, then show how its optimization can be unfolded with a novel end-toend deep architecture. The proposed architecture is a convolutional recurrent neural network that integrates visual and temporal knowledge of both global and local scales in principled manner. To further improve the reconstruction, we propose a differentiable directional event filtering module to effectively extract rich boundary prior from the evolution of events. We conduct extensive experiments on the synthetic GoPro dataset and a large newly introduced dataset captured by a DAVIS240C camera. The proposed approach achieves state-of-the-art reconstruction quality, and generalizes better to handling real-world motion blur.