CVPR 2020 论文列表

Recent deep learning approaches have achieved impressive performance on visual sound separation tasks. However, these approaches are mostly built on appearance and optical flow like motion feature representations, which exhibit limited abilities to find the correlations between audio signals and visual points, especially when separating multiple instruments of the same types, such as multiple violins in a scene. To address this, we propose "Music Gesture," a keypoint-based structured representation to explicitly model the body and finger movements of musicians when they perform music. We first adopt a context-aware graph network to integrate visual semantic context with body dynamics and then apply an audio-visual fusion model to associate body movements with the corresponding audio signals. Experimental results on three music performance datasets show: 1) strong improvements upon benchmark metrics for hetero-musical separation tasks (i.e. different instruments); 2) new ability for effective homo-musical separation for piano, flute, and trumpet duets, which to our best knowledge has never been achieved with alternative methods.

The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this annotation dependency, we propose Multiview-Consistent Semi Supervised Learning (MCSS) framework that utilizes similarity in pose information from unannotated, uncalibrated but synchronized multi-view videos of human motions as additional weak supervision signal to guide 3D human pose regression. Our framework applies hard-negative mining based on temporal relations in multi-view videos to arrive at a multi-view consistent pose embedding and when jointly trained with limited 3D pose annotations, our approach improves the baseline by 25% and state-of-the-art by 8.7%, whilst using substantially smaller networks. Lastly, but importantly, we demonstrate the advantages of the learned embedding and establish view-invariant pose retrieval benchmarks on two popular, publicly available multi-view human pose datasets, Human 3.6M and MPI-INF-3DHP, to facilitate future research.

Classification and localization are two pillars of visual object detectors. However, in CNN-based detectors, these two modules are usually optimized under a fixed set of candidate (or anchor) bounding boxes. This configuration significantly limits the possibility to jointly optimize classification and localization. In this paper, we propose a Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector. Our approach, referred to as Multiple Anchor Learning (MAL), constructs anchor bags and selects the most representative anchors from each bag. Such an iterative selection process is potentially NP-hard to optimize. To address this issue, we solve MAL by repetitively depressing the confidence of selected anchors by perturbing their corresponding features. In an adversarial selection-depression manner, MAL not only pursues optimal solutions but also fully leverages multiple anchors/features to learn a detection model. Experiments show that MAL improves the baseline RetinaNet with significant margins on the commonly used MS-COCO object detection benchmark and achieves new state-of-the-art detection performance compared with recent methods.

In this paper, we investigate the problem of anticipating future dynamics, particularly the future location of other vehicles and pedestrians, in the view of a moving vehicle. We approach two fundamental challenges: (1) the partial visibility due to the egocentric view with a single RGB camera and considerable field-of-view change due to the egomotion of the vehicle; (2) the multimodality of the distribution of future states. In contrast to many previous works, we do not assume structural knowledge from maps. We rather estimate a reachability prior for certain classes of objects from the semantic map of the present image and propagate it into the future using the planned egomotion. Experiments show that the reachability prior combined with multi-hypotheses learning improves multimodal prediction of the future location of tracked objects and, for the first time, the emergence of new objects. We also demonstrate promising zero-shot transfer to unseen datasets.

Recent developments in image classification and natural language processing, coupled with the rapid growth in social media usage, have enabled fundamental advances in detecting breaking events around the world in real-time. Emergency response is one such area that stands to gain from these advances. By processing billions of texts and images a minute, events can be automatically detected to enable emergency response workers to better assess rapidly evolving situations and deploy resources accordingly. To date, most event detection techniques in this area have focused on image-only or text-only approaches, limiting detection performance and impacting the quality of information delivered to crisis response teams. In this paper, we present a new multimodal fusion method that leverages both images and texts as input. In particular, we introduce a cross-attention module that can filter uninformative and misleading components from weak modalities on a sample by sample basis. In addition, we employ a multimodal graph-based approach to stochastically transition between embeddings of different multimodal pairs during training to better regularize the learning process as well as dealing with limited training data by constructing new matched pairs from different samples. We show that our method outperforms the unimodal approaches and strong multimodal baselines by a large margin on three crisis-related tasks.

We propose a new method for cancer subtype classification from histopathological images, which can automatically detect tumor-specific features in a given whole slide image (WSI). The cancer subtype should be classified by referring to a WSI, i.e., a large-sized image (typically 40,000x40,000 pixels) of an entire pathological tissue slide, which consists of cancer and non-cancer portions. One difficulty arises from the high cost associated with annotating tumor regions in WSIs. Furthermore, both global and local image features must be extracted from the WSI by changing the magnifications of the image. In addition, the image features should be stably detected against the differences of staining conditions among the hospitals/specimens. In this paper, we develop a new CNN-based cancer subtype classification method by effectively combining multiple-instance, domain adversarial, and multi-scale learning frameworks in order to overcome these practical difficulties. When the proposed method was applied to malignant lymphoma subtype classifications of 196 cases collected from multiple hospitals, the classification performance was significantly better than the standard CNN or other conventional methods, and the accuracy compared favorably with that of standard pathologists.

We present an end-to-end Neural Human Renderer (NHR) for dynamic human captures under the multi-view setting. NHR adopts PointNet++ for feature extraction (FE) to enable robust 3D correspondence matching on low quality, dynamic 3D reconstructions. To render new views, we map 3D features onto the target camera as a 2D feature map and employ an anti-aliased CNN to handle holes and noises. Newly synthesized views from NHR can be further used to construct visual hulls to handle textureless and/or dark regions such as black clothing. Comprehensive experiments show NHR significantly outperforms the state-of-the-art neural and image-based rendering techniques, especially on hands, hair, nose, foot, etc.

Referring expression comprehension (REC) and segmentation (RES) are two highly-related tasks, which both aim at identifying the referent according to a natural language expression. In this paper, we propose a novel Multi-task Collaborative Network (MCN) to achieve a joint learning of REC and RES for the first time. In MCN, RES can help REC to achieve better language-vision alignment, while REC can help RES to better locate the referent. In addition, we address a key challenge in this multi-task setup, i.e., the prediction conflict, with two innovative designs namely, Consistency Energy Maximization (CEM) and Adaptive Soft Non-Located Suppression (ASNLS). Specifically, CEM enables REC and RES to focus on similar visual regions by maximizing the consistency energy between two tasks. ASNLS supresses the response of unrelated regions in RES based on the prediction of REC. To validate our model, we conduct extensive experiments on three benchmark datasets of REC and RES, i.e., RefCOCO, RefCOCO+ and RefCOCOg. The experimental results report the significant performance gains of MCN over all existing methods, i.e., up to +7.13% for REC and +11.50% for RES over SOTA, which well confirm the validity of our model for joint REC and RES learning.

Rain streaks in the air appear in various blurring degrees and resolutions due to different distances from their positions to the camera. Similar rain patterns are visible in a rain image as well as its multi-scale (or multi-resolution) versions, which makes it possible to exploit such complementary information for rain streak representation. In this work, we explore the multi-scale collaborative representation for rain streaks from the perspective of input image scales and hierarchical deep features in a unified framework, termed multi-scale progressive fusion network (MSPFN) for single image rain streak removal. For the similar rain streaks at different positions, we employ recurrent calculation to capture the global texture, thus allowing to explore the complementary and redundant information at the spatial dimension to characterize target rain streaks. Besides, we construct multi-scale pyramid structure, and further introduce the attention mechanism to guide the fine fusion of these correlated information from different scales. This multi-scale progressive fusion strategy not only promotes the cooperative representation, but also boosts the end-to-end training. Our proposed method is extensively evaluated on several benchmark datasets and achieves the state-of-the-art results. Moreover, we conduct experiments on joint deraining, detection, and segmentation tasks, and inspire a new research direction of vision task driven image deraining. The source code is available at https://github.com/kuihua/MSPFN.

Deep-learning based salient object detection methods achieve great progress. However, the variable scale and unknown category of salient objects are great challenges all the time. These are closely related to the utilization of multi-level and multi-scale features. In this paper, we propose the aggregate interaction modules to integrate the features from adjacent levels, in which less noise is introduced because of only using small up-/down-sampling rates. To obtain more efficient multi-scale features from the integrated features, the self-interaction modules are embedded in each decoder unit. Besides, the class imbalance issue caused by the scale variation weakens the effect of the binary cross entropy loss and results in the spatial inconsistency of the predictions. Therefore, we exploit the consistency-enhanced loss to highlight the fore-/back-ground difference and preserve the intra-class consistency. Experimental results on five benchmark datasets demonstrate that the proposed method without any post-processing performs favorably against 23 state-of-the-art approaches. The source code will be publicly available at https://github.com/lartpang/MINet.

Classical subspace clustering methods often assume that the raw form data lie in a union of the low-dimension linear subspace. This assumption is too strict in practice, which largely limits the generalization of subspace clustering. To tackle this issue, deep subspace clustering (DSC) networks based on deep autoencoder (DAE) have been proposed, which non-linearly map the raw form data into a latent space well-adapted to subspace clustering. However, existing DSC models ignore the important multi-scale information embedded in DAE, thus abandon the much more useful deep features, leading their suboptimal clustering results. In this paper, we propose the Multi-Scale Fusion Subspace Clustering Using Similarity Constraint (SC-MSFSC) network, which learns a more discriminative self-expression coefficient matrix by a novel multi-scale fusion module. More importantly, it introduces a similarity constraint module to guide the fused self-expression coefficient matrix in training. Specifically, the multi-scale fusion module is framed to generate the self-expression coefficient matrix of each convolutional layer in DAE and then fuses them with the convolutional kernel. In addition, the similarity constraint module is to supervise the fused self-expression coefficient matrix by the designed similarity matrix. Extensive experimental results on four benchmark datasets demonstrate the superiority of our new model against state-of-the-art methods.

In this paper, we propose a Multi-Scale Boosted Dehazing Network with Dense Feature Fusion based on the U-Net architecture. The proposed method is designed based on two principles, boosting and error feedback, and we show that they are suitable for the dehazing problem. By incorporating the Strengthen-Operate-Subtract boosting strategy in the decoder of the proposed model, we develop a simple yet effective boosted decoder to progressively restore the haze-free image. To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme. We show that the dense feature fusion module can simultaneously remedy the missing spatial information from high-resolution features and exploit the non-adjacent features. Extensive evaluations demonstrate that the proposed model performs favorably against the state-of-the-art approaches on the benchmark datasets as well as real-world hazy images.

Point clouds provide intrinsic geometric information and surface context for scene understanding. Existing methods for point cloud segmentation require a large amount of fully labeled data. Using advanced depth sensors, collection of large scale 3D dataset is no longer a cumbersome process. However, manually producing point-level label on the large scale dataset is time and labor-intensive. In this paper, we propose a weakly supervised approach to predict point-level results using weak labels on 3D point clouds. We introduce our multi-path region mining module to generate pseudo point-level labels from a classification network trained with weak labels. It mines the localization cues for each class from various aspects of the network feature using different attention modules. Then, we use the point-level pseudo label to train a point cloud segmentation network in a fully supervised manner. To the best of our knowledge, this is the first method that uses cloud-level weak labels on raw 3D space to train a point cloud semantic segmentation network. In our setting, the 3D weak labels only indicate the classes that appeared in our input sample. We discuss both scene- and subcloud-level weakly labels on raw 3D point cloud data and perform in-depth experiments on them. On ScanNet dataset, our result trained with subcloud-level labels is compatible with some fully supervised methods.

We introduce a scalable approach for object pose estimation trained on simulated RGB views of multiple 3D models together. We learn an encoding of object views that does not only describe an implicit orientation of all objects seen during training, but can also relate views of untrained objects. Our single-encoder-multi-decoder network is trained using a technique we denote "multi-path learning": While the encoder is shared by all objects, each decoder only reconstructs views of a single object. Consequently, views of different instances do not have to be separated in the latent space and can share common features. The resulting encoder generalizes well from synthetic to real data and across various instances, categories, model types and datasets. We systematically investigate the learned encodings, their generalization, and iterative refinement strategies on the ModelNet40 and T-LESS dataset. Despite training jointly on multiple objects, our 6D Object Detection pipeline achieves state-of-the-art results on T-LESS at much lower runtimes than competing approaches.

Human motion segmentation based on transfer subspace learning is a rising interest in action-related tasks. Although progress has been made, there are still several issues within the existing methods. First, existing methods transfer knowledge from source data to target tasks by learning domain-invariant features, but they ignore to preserve domain-specific knowledge. Second, the transfer subspace learning is employed in either low-level or high-level feature spaces, but few methods consider fusing multi-level features for subspace learning. To this end, we propose a novel multi-mutual consistency induced transfer subspace learning framework for human motion segmentation. Specifically, our model factorizes the source and target data into distinct multi-layer feature spaces and reduces the distribution gap between them through a multi-mutual consistency learning strategy. In this way, the domain-specific knowledge and domain-invariant properties can be explored simultaneously. Our model also conducts the transfer subspace learning on different layers to capture multi-level structural information. Further, to preserve the temporal correlations, we project the learned representations into a block-like space. The proposed model is efficiently optimized by using the Augmented Lagrange Multiplier (ALM) algorithm. Experimental results on four human motion datasets demonstrate the effectiveness of our method over other state-of-the-art approaches.

The key of image and sentence matching is to accurately measure the visual-semantic similarity between an image and a sentence. However, most existing methods make use of only the intra-modality relationship within each modality or the inter-modality relationship between image regions and sentence words for the cross-modal matching task. Different from them, in this work, we propose a novel MultiModality Cross Attention (MMCA) Network for image and sentence matching by jointly modeling the intra-modality and inter-modality relationships of image regions and sentence words in a unified deep model. In the proposed MMCA, we design a novel cross-attention mechanism, which is able to exploit not only the intra-modality relationship within each modality, but also the inter-modality relationship between image regions and sentence words to complement and enhance each other for image and sentence matching. Extensive experimental results on two standard benchmarks including Flickr30K and MS-COCO demonstrate that the proposed model performs favorably against state-of-the-art image and sentence matching methods.

Answering questions that require reading texts in an image is challenging for current models. One key difficulty of this task is that rare, polysemous, and ambiguous words frequently appear in images, e.g., names of places, products, and sports teams. To overcome this difficulty, only resorting to pre-trained word embedding models is far from enough. A desired model should utilize the rich information in multiple modalities of the image to help understand the meaning of scene texts, e.g., the prominent text on a bottle is most likely to be the brand. Following this idea, we propose a novel VQA approach, Multi-Modal Graph Neural Network (MM-GNN). It first represents an image as a graph consisting of three sub-graphs, depicting visual, semantic, and numeric modalities respectively. Then, we introduce three aggregators which guide the message passing from one graph to another to utilize the contexts in various modalities, so as to refine the features of nodes. The updated nodes have better features for the downstream question answering module. Experimental evaluations show that our MM-GNN represents the scene texts better and obviously facilitates the performances on two VQA tasks that require reading scene texts.

Fine-grained action recognition datasets exhibit environmental bias, where multiple video sequences are captured from a limited number of environments. Training a model in one environment and deploying in another results in a drop in performance due to an unavoidable domain shift. Unsupervised Domain Adaptation (UDA) approaches have frequently utilised adversarial training between the source and target domains. However, these approaches have not explored the multi-modal nature of video within each domain. In this work we exploit the correspondence of modalities as a self-supervised alignment approach for UDA in addition to adversarial alignment (Fig. 1). We test our approach on three kitchens from the large-scale EPIC-Kitchens dataset, using two modalities commonly employed for action recognition: RGB and Optical Flow. We show that multi-modal self-supervision alone improves the performance over source-only training by 2.4% on average. We then combine adversarial training with multi-modal self-supervision, showing that our approach outperforms other UDA methods by 3%.

Video-based person re-identification (reID) aims at matching the same person across video clips. It is a challenging task due to the existence of redundancy among frames, newly revealed appearance, occlusion, and motion blurs. In this paper, we propose an attentive feature aggregation module, namely Multi-Granularity Reference-aided Attentive Feature Aggregation (MG-RAFA), to delicately aggregate spatio-temporal features into a discriminative video-level feature representation. In order to determine the contribution/importance of a spatial-temporal feature node, we propose to learn the attention from a global view with convolutional operations. Specifically, we stack its relations, i.e.no, pairwise correlations with respect to a representative set of reference feature nodes (S-RFNs) that represents global video information, together with the feature itself to infer the attention. Moreover, to exploit the semantics of different levels, we propose to learn multi-granularity attentions based on the relations captured at different granularities. Extensive ablation studies demonstrate the effectiveness of our attentive feature aggregation module MG-RAFA. Our framework achieves the state-of-the-art performance on three benchmark datasets.