CVPR 2020 论文列表

Fine-grained visual categorization has long been considered as an important problem, however, its real application is still restricted, since precisely annotating a large fine-grained image dataset is a laborious task and requires expert-level human knowledge. A solution to this problem is applying domain adaptation approaches to fine-grained scenarios, where the key idea is to discover the commonality between existing fine-grained image datasets and massive unlabeled data in the wild. The main technical bottleneck lies in that the large inter-domain variation will deteriorate the subtle boundaries of small inter-class variation during domain alignment. This paper presents the Progressive Adversarial Networks (PAN) to align fine-grained categories across domains with a curriculum-based adversarial learning framework. In particular, throughout the learning process, domain adaptation is carried out through all multi-grained features, progressively exploiting the label hierarchy from coarse to fine. The progressive learning is applied upon both category classification and domain alignment, boosting both the discriminability and the transferability of the fine-grained features. Our method is evaluated on three benchmarks, two of which are proposed by us, and it outperforms the state-of-the-art domain adaptation methods.

Domain adaptive image retrieval includes single-domain retrieval and cross-domain retrieval. Most of the existing image retrieval methods only focus on single-domain retrieval, which assumes that the distributions of retrieval databases and queries are similar. However, in practical application, the discrepancies between retrieval databases often taken in ideal illumination/pose/background/camera conditions and queries usually obtained in uncontrolled conditions are very large. In this paper, considering the practical application, we focus on challenging cross-domain retrieval. To address the problem, we propose an effective method named Probability Weighted Compact Feature Learning (PWCF), which provides inter-domain correlation guidance to promote cross-domain retrieval accuracy and learns a series of compact binary codes to improve the retrieval speed. First, we derive our loss function through the Maximum A Posteriori Estimation (MAP): Bayesian Perspective (BP) induced focal-triplet loss, BP induced quantization loss and BP induced classification loss. Second, we propose a common manifold structure between domains to explore the potential correlation across domains. Considering the original feature representation is biased due to the inter-domain discrepancy, the manifold structure is difficult to be constructed. Therefore, we propose a new feature named Histogram Feature of Neighbors (HFON) from the sample statistics perspective. Extensive experiments on various benchmark databases validate that our method outperforms many state-of-the-art image retrieval methods for domain adaptive image retrieval. The source code is available at https://github.com/fuxianghuang1/PWCF .

We study a new research problem of probabilistic future frames prediction from a sequence of noisy inputs, which is useful because it is difficult to guarantee the quality of input frames in practical spatiotemporal prediction applications. It is also challenging because it involves two levels of uncertainty: the perceptual uncertainty from noisy observations and the dynamics uncertainty in forward modeling. In this paper, we propose to tackle this problem with an end-to-end trainable model named Bayesian Predictive Network (BP-Net). Unlike previous work in stochastic video prediction that assumes spatiotemporal coherence and therefore fails to deal with perceptual uncertainty, BP-Net models both levels of uncertainty in an integrated framework. Furthermore, unlike previous work that can only provide unsorted estimations of future frames, BP-Net leverages a differentiable sequential importance sampling (SIS) approach to make future predictions based on the inference of underlying physical states, thereby providing sorted prediction candidates in accordance with the SIS importance weights, i.e., the confidences. Our experiment results demonstrate that BP-Net remarkably outperforms existing approaches on predicting future frames from noisy data.

Unsupervised embedding learning aims at extracting low-dimensional visually meaningful representations from large-scale unlabeled images, which can then be directly used for similarity-based search. This task faces two major challenges: 1) mining positive supervision from highly similar fine-grained classes and 2) generating to unseen testing categories. To tackle these issues, this paper proposes a probabilistic structural latent representation (PSLR), which incorporates an adaptable softmax embedding to approximate the positive concentrated and negative instance separated properties in the graph latent space. It improves the discriminability by enlarging the positive/negative difference without introducing any additional computational cost while maintaining high learning efficiency. To address the limited supervision using data augmentation, a smooth variational reconstruction loss is introduced by modeling the intra-instance variance, which improves the robustness. Extensive experiments demonstrate the superiority of PSLR over state-of-the-art unsupervised methods on both seen and unseen categories with cosine similarity. Code is available at https://github.com/mangye16/PSLR

Visual tracking is fundamentally the problem of regressing the state of the target in each video frame. While significant progress has been achieved, trackers are still prone to failures and inaccuracies. It is therefore crucial to represent the uncertainty in the target estimation. Although current prominent paradigms rely on estimating a state-dependent confidence score, this value lacks a clear probabilistic interpretation, complicating its use. In this work, we therefore propose a probabilistic regression formulation and apply it to tracking. Our network predicts the conditional probability density of the target state given an input image. Crucially, our formulation is capable of modeling label noise stemming from inaccurate annotations and ambiguities in the task. The regression network is trained by minimizing the Kullback-Leibler divergence. When applied for tracking, our formulation not only allows a probabilistic representation of the output, but also substantially improves the performance. Our tracker sets a new state-of-the-art on six datasets, achieving 59.8% AUC on LaSOT and 75.8% Success on TrackingNet. The code and models are available at https://github.com/visionml/pytracking.

Encoder-decoder networks have found widespread use in various dense prediction tasks. However, the strong reduction of spatial resolution in the encoder leads to a loss of location information as well as boundary artifacts. To address this, image-adaptive post-processing methods have shown beneficial by leveraging the high-resolution input image(s) as guidance data. We extend such approaches by considering an important orthogonal source of information: the network's confidence in its own predictions. We introduce probabilistic pixel-adaptive convolutions (PPACs), which not only depend on image guidance data for filtering, but also respect the reliability of per-pixel predictions. As such, PPACs allow for image-adaptive smoothing and simultaneously propagating pixels of high confidence into less reliable regions, while respecting object boundaries. We demonstrate their utility in refinement networks for optical flow and semantic segmentation, where PPACs lead to a clear reduction in boundary artifacts. Moreover, our proposed refinement step is able to substantially improve the accuracy on various widely used benchmarks.

Contour shape alignment is a fundamental but challenging problem in computer vision, especially when the observations are partial, noisy, and largely misaligned. Recent ConvNet-based architectures that were proposed to align image structures tend to fail with contour representation of shapes, mostly due to the use of proximity-insensitive pixel-wise similarity measures as loss functions in their training processes. This work presents a novel ConvNet, "ProAlignNet," that accounts for large scale misalignments and complex transformations between the contour shapes. It infers the warp parameters in a multi-scale fashion with progressively increasing complex transformations over increasing scales. It learns --without supervision-- to align contours, agnostic to noise and missing parts, by training with a novel loss function which is derived an upperbound of a proximity-sensitive and local shape-dependent similarity metric that uses classical Morphological Chamfer Distance Transform. We evaluate the reliability of these proposals on a simulated MNIST noisy contours dataset via some basic sanity check experiments. Next, we demonstrate the effectiveness of the proposed models in two real-world applications of (i) aligning geo-parcel data to aerial image maps and (ii) refining coarsely annotated segmentation labels. In both applications, the proposed models consistently perform superior to state-of-the-art methods.

With increasing ethical and legal concerns on privacy for deep models in visual recognition, differential privacy has emerged as a mechanism to disguise membership of sensitive data in training datasets. Recent methods like Private Aggregation of Teacher Ensembles (PATE) leverage a large ensemble of teacher models trained on disjoint subsets of private data, to transfer knowledge to a student model with privacy guarantees. However, labeled vision data is often expensive and datasets, when split into many disjoint training sets, lead to significantly sub-optimal accuracy and thus hardly sustain good privacy bounds. We propose a practically data-efficient scheme based on private release of k-nearest neighbor (kNN) queries, which altogether avoids splitting the training dataset. Our approach allows the use of privacy-amplification by subsampling and iterative refinement of the kNN feature embedding. We rigorously analyze the theoretical properties of our method and demonstrate strong experimental performance on practical computer vision datasets for face attribute recognition and person reidentification. In particular, we achieve comparable or better accuracy than PATE while reducing more than 90% of the privacy loss, thereby providing the "most practical method to-date" for private deep learning in computer vision.

Contemporary deep learning based semantic inpainting can be approached from two directions. First, and the more explored, approach is to train an offline deep regression network over the masked pixels with an additional refinement by adversarial training. This approach requires a single feed-forward pass for inpainting at inference. Another promising, yet unexplored approach is to first train a generative model to map a latent prior distribution to natural image manifold and during inference time search for the best-matching prior to reconstruct the signal. The primary aversion towards the latter genre is due to its inference time iterative optimization and difficulty to scale to higher resolution. In this paper, going against the general trend, we focus on the second paradigm of inpainting and address both of its mentioned problems. Most importantly, we learn a data driven parametric network to directly predict a matching prior for a given masked image. This converts an iterative paradigm to a single feed forward inference pipeline with around 800X speedup. We also regularize our network with structural prior (computed from the masked image itself) which helps in better preservation of pose and size of the object to be inpainted. Moreover, to extend our model for sequence reconstruction, we propose a recurrent net based grouped latent prior learning. Finally, we leverage recent advancements in high resolution GAN training to scale our inpainting network to 256X256. Experiments (spanning across resolutions from 64X64 to 256X256) conducted on SVHN, Standford Cars, CelebA, CelebA-HQ and ImageNet image datasets, and FaceForensics video datasets reveal that we consistently improve upon contemporary benchmarks from both schools of approaches.

It is a common paradigm in object detection frameworks to treat all samples equally and target at maximizing the performance on average. In this work, we revisit this paradigm through a careful study on how different samples contribute to the overall performance measured in terms of mAP. Our study suggests that the samples in each mini-batch are neither independent nor equally important, and therefore a better classifier on average does not necessarily result in higher mAP. Motivated by this study, we propose the notion of Prime Samples, those that play a key role in driving the detection performance. We further develop a simple yet effective sampling and learning strategy called PrIme Sample Attention (PISA) that directs the focus of the training process towards such samples. Our experiments demonstrate that it is often more effective to focus on prime samples than hard samples when training a detector. Particularly, on the MSCOCO dataset, PISA outperforms the random sampling baseline and hard mining schemes, e.g. OHEM and Focal Loss, consistently by around 2% on both single-stage and two-stage detectors, even with a strong backbone ResNeXt-101. Code is available at: https://github.com/open-mmlab/mmdetection.

Current methods for depth map prediction from monocular images tend to predict smooth, poorly localized contours for the occlusion boundaries in the input image. This is unfortunate as occlusion boundaries are important cues to recognize objects, and as we show, may lead to a way to discover new objects from scene reconstruction. To improve predicted depth maps, recent methods rely on various forms of filtering or predict an additive residual depth map to refine a first estimate. We instead learn to predict, given a depth map predicted by some reconstruction method, a 2D displacement field able to re-sample pixels around the occlusion boundaries into sharper reconstructions. Our method can be applied to the output of any depth estimation method, in an end-to-end trainable fashion. For evaluation, we manually annotated the occlusion boundaries in all the images in the test split of popular NYUv2-Depth dataset. We show that our approach improves the localization of occlusion boundaries for all state-of-the-art monocular depth estimation methods that we could evaluate, without degrading the depth accuracy for the rest of the images.

Autonomous vehicles commonly rely on highly detailed birds-eye-view maps of their environment, which capture both static elements of the scene such as road layout as well as dynamic elements such as other cars and pedestrians. Generating these map representations on the fly is a complex multi-stage process which incorporates many important vision-based elements, including ground plane estimation, road segmentation and 3D object detection. In this work we present a simple, unified approach for estimating these map representations directly from monocular images using a single end-to-end deep learning architecture. For the maps themselves we adopt a semantic Bayesian occupancy grid framework, allowing us to trivially accumulate information over multiple cameras and timesteps. We demonstrate the effectiveness of our approach by evaluating against several challenging baselines on the NuScenes and Argoverse datasets, and show that we are able to achieve a relative improvement of 9.1% and 22.3% respectively compared to the best-performing existing method.

Multiple instance learning (MIL) is a typical weakly-supervised learning method where the label is associated with a bag of instances instead of a single instance. Despite extensive research over past years, effectively deploying MIL remains an open and challenging problem, especially when the commonly assumed standard multiple instance (SMI) assumption is not satisfied. In this paper, we propose a multiple instance learning method based on deep graph convolutional network and feature selection (FS-GCN-MIL) for histopathological image classification. The proposed method consists of three components, including instance-level feature extraction, instance-level feature selection, and bag-level classification. We develop a self-supervised learning mechanism to train the feature extractor based on a combination model of variational autoencoder and generative adversarial network (VAE-GAN). Additionally, we propose a novel instance-level feature selection method to select the discriminative instance features. Furthermore, we employ a graph convolutional network (GCN) for learning the bag-level representation and then performing the classification. We apply the proposed method in the prediction of lymph node metastasis using histopathological images of colorectal cancer. Experimental results demonstrate that the proposed method achieves superior performance compared to the state-of-the-art methods.

Human gaze behavior prediction is important for behavioral vision and for computer vision applications. Most models mainly focus on predicting free-viewing behavior using saliency maps, but do not generalize to goal-directed behavior, such as when a person searches for a visual target object. We propose the first inverse reinforcement learning (IRL) model to learn the internal reward function and policy used by humans during visual search. We modeled the viewer's internal belief states as dynamic contextual belief maps of object locations. These maps were learned and then used to predict behavioral scanpaths for multiple target categories. To train and evaluate our IRL model we created COCO-Search18, which is now the largest dataset of high-quality search fixations in existence. COCO-Search18 has 10 participants searching for each of 18 target-object categories in 6202 images, making about 300,000 goal-directed fixations. When trained and evaluated on COCO-Search18, the IRL model outperformed baseline models in predicting search fixation scanpaths, both in terms of similarity to human search behavior and search efficiency. Finally, reward maps recovered by the IRL model reveal distinctive target-dependent patterns of object prioritization, which we interpret as a learned object context.

With rapid progress in high-throughput genotyping and neuroimaging, researches of complex brain disorders, such as Alzheimer's Disease (AD), have gained significant attention in recent years. Many prediction models have been studied to relate neuroimaging measures to cognitive status over the progressions when these disease develops. Missing data is one of the biggest challenge in accurate cognitive score prediction of subjects in longitudinal neuroimaging studies. To tackle this problem, in this paper we propose a novel formulation to learn an enriched representation for imaging biomarkers that can simultaneously capture both the information conveyed by baseline neuroimaging records and that by progressive variations of varied counts of available follow-up records over time. While the numbers of the brain scans of the participants vary, the learned biomarker representation for every participant is a fixed-length vector, which enable us to use traditional learning models to study AD developments. Our new objective is formulated to maximize the ratio of the summations of a number of L1-norm distances for improved robustness, which, though, is difficult to efficiently solve in general. Thus we derive a new efficient iterative solution algorithm and rigorously prove its convergence. We have performed extensive experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. A performance gain has been achieved to predict four different cognitive scores, when we compare the original baseline representations against the learned representations with enrichments. These promising empirical results have demonstrated improved performances of our new method that validate its effectiveness.

Occluded person re-identification is a challenging task as the appearance varies substantially with various obstacles, especially in the crowd scenario. To address this issue, we propose a Pose-guided Visible Part Matching (PVPM) method that jointly learns the discriminative features with pose-guided attention and self-mines the part visibility in an end-to-end framework. Specifically, the proposed PVPM includes two key components: 1) pose-guided attention (PGA) method for part feature pooling that exploits more discriminative local features; 2) pose-guided visibility predictor (PVP) that estimates whether a part suffers the occlusion or not. As there are no ground truth training annotations for the occluded part, we turn to utilize the characteristic of part correspondence in positive pairs and self-mining the correspondence scores via graph matching. The generated correspondence scores are then utilized as pseudo-labels for visibility predictor (PVP). Experimental results on three reported occluded benchmarks show that the proposed method achieves competitive performance to state-of-the-art methods. The source codes are available at https://github.com/hh23333/PVPM

In this paper, we propose PolyTransform, a novel instance segmentation algorithm that produces precise, geometry-preserving masks by combining the strengths of prevailing segmentation approaches and modern polygon-based methods. In particular, we first exploit a segmentation network to generate instance masks. We then convert the masks into a set of polygons that are then fed to a deforming network that transforms the polygons such that they better fit the object boundaries. Our experiments on the challenging Cityscapes dataset show that our PolyTransform significantly improves the performance of the backbone instance segmentation network and ranks 1st on the Cityscapes test-set leaderboard. We also show impressive gains in the interactive annotation setting.

As an effective black-box adversarial attack, decision-based methods polish adversarial noise by querying the target model. Among them, boundary attack is widely applied due to its powerful noise compression capability, especially when combined with transfer-based methods. Boundary attack splits the noise compression into several independent sampling processes, repeating each query with a constant sampling setting. In this paper, we demonstrate the advantage of using current noise and historical queries to customize the variance and mean of sampling in boundary attack to polish adversarial noise. We further reveal the relationship between the initial noise and the compressed noise in boundary attack. We propose Customized Adversarial Boundary (CAB) attack that uses the current noise to model the sensitivity of each pixel and polish adversarial noise of each image with a customized sampling setting. On the one hand, CAB uses current noise as a prior belief to customize the multivariate normal distribution. On the other hand, CAB keeps the new samplings away from historical failed queries to avoid similar mistakes. Experimental results measured on several image classification datasets emphasizes the validity of our method.

We present a novel formulation to removing reflection from polarized images in the wild. We first identify the misalignment issues of existing reflection removal datasets where the collected reflection-free images are not perfectly aligned with input mixed images due to glass refraction. Then we build a new dataset with more than 100 types of glass in which obtained transmission images are perfectly aligned with input mixed images. Second, capitalizing on the special relationship between reflection and polarized light, we propose a polarized reflection removal model with a two-stage architecture. In addition, we design a novel perceptual NCC loss that can improve the performance of reflection removal and general image decomposition tasks. We conduct extensive experiments, and results suggest that our model outperforms state-of-the-art methods on reflection removal.