CVPR 2020 论文列表

Unsupervised learning of identity-discriminative visual feature is appealing in real-world tasks where manual labelling is costly. However, the images of an identity can be visually discrepant when images are taken under different states, e.g. different camera views and poses. This visual discrepancy leads to great difficulty in unsupervised discriminative learning. Fortunately, in real-world tasks we could often know the states without human annotation, e.g. we can easily have the camera view labels in person re-identification and facial pose labels in face recognition. In this work we propose utilizing the state information as weak supervision to address the visual discrepancy caused by different states. We formulate a simple pseudo label model and utilize the state information in an attempt to refine the assigned pseudo labels by the weakly supervised decision boundary rectification and weakly supervised feature drift regularization. We evaluate our model on unsupervised person re-identification and pose-invariant face recognition. Despite the simplicity of our method, it could outperform the state-of-the-art results on Duke-reID, MultiPIE and CFP datasets with a standard ResNet-50 backbone. We also find our model could perform comparably with the standard supervised fine-tuning results on the three datasets. Code is available at https://github.com/KovenYu/state-information.

Some stereo matching algorithms based on deep learning have been proposed and achieved state-of-the-art performances since some public large-scale datasets were put online. However, the disparity in smooth regions and detailed regions is still difficult to accurately estimate simultaneously. This paper proposes a novel stereo matching method called WaveletStereo, which learns the wavelet coefficients of the disparity rather than the disparity itself. The WaveletStereo consists of several sub-modules, where the low-frequency sub-module generates the low-frequency wavelet coefficients, which aims at learning global context information and well handling the low-frequency regions such as textureless surfaces, and the others focus on the details. In addition, a densely connected atrous spatial pyramid block is introduced for better learning the multi-scale image features. Experimental results show the effectiveness of the proposed method, which achieves state-of-the-art performance on the large-scale test dataset Scene Flow.

Modern smartphone cameras can match traditional DSLR cameras in many areas thanks to the introduction of camera arrays and multi-frame processing. Among all types of DSLR effects, the narrow depth of field (DoF) or so called bokeh probably arouses most interest. Today's smartphones try to overcome the physical lens and sensor limitations by introducing computational methods that utilize a depth map to synthesize the narrow DoF effect from all-in-focus images. However, a high quality depth map remains to be the key differentiator between computational bokeh and DSLR optical bokeh. Empowered by a novel wavelet synthesis network architecture, we have greatly narrowed the gap between DSLR and smartphone camera in terms of the bokeh more than ever before. We describe three key Modern smartphone cameras can match traditional digital single lens reflex (DSLR) cameras in many areas thanks to the introduction of camera arrays and multi-frame processing. Among all types of DSLR effects, the narrow depth of field (DoF) or so called bokeh probably arouses most interest. Today's smartphones try to overcome the physical lens and sensor limitations by introducing computational methods that utilize a depth map to synthesize the narrow DoF effect from all-in-focus images. However, a high quality depth map remains to be the key differentiator between computational bokeh and DSLR optical bokeh. Empowered by a novel wavelet synthesis network architecture, we have narrowed the gap between DSLR and smartphone camera in terms of bokeh more than ever before. We describe three key enablers of our bokeh solution: a synthetic graphics engine to generate training data with precisely prescribed characteristics that match the real smartphone captures, a novel wavelet synthesis neural network (WSN) architecture to produce unprecedented high definition disparity map promptly on smartphones, and a new evaluation metric to quantify the quality of the disparity map for real images from the bokeh rendering perspective. Experimental results show that the disparity map produced from our neural network achieves much better accuracy than the other state-of-the-art CNN based algorithms. Combining the high resolution disparity map with our rendering algorithm, we demonstrate visually superior bokeh pictures compared with existing top rated flagship smartphones listed on the DXOMARK mobiles.

Convolutional Neural Networks (CNNs) are generally prone to noise interruptions, i.e., small image noise can cause drastic changes in the output. To suppress the noise effect to the final predication, we enhance CNNs by replacing max-pooling, strided-convolution, and average-pooling with Discrete Wavelet Transform (DWT). We present general DWT and Inverse DWT (IDWT) layers applicable to various wavelets like Haar, Daubechies, and Cohen, etc., and design wavelet integrated CNNs (WaveCNets) using these layers for image classification. In WaveCNets, feature maps are decomposed into the low-frequency and high-frequency components during the down-sampling. The low-frequency component stores main information including the basic object structures, which is transmitted into the subsequent layers to extract robust high-level features. The high-frequency components, containing most of the data noise, are dropped during inference to improve the noise-robustness of the WaveCNets. Our experimental results on ImageNet and ImageNet-C (the noisy version of ImageNet) show that WaveCNets, the wavelet integrated versions of VGG, ResNets, and DenseNet, achieve higher accuracy and better noise-robustness than their vanilla versions.

Generative convolutional deep neural networks, e.g. popular GAN architectures, are relying on convolution based up-sampling methods to produce non-scalar outputs like images or video sequences. In this paper, we show that common up-sampling methods, i.e. known as up-convolution or transposed convolution, are causing the inability of such models to reproduce spectral distributions of natural training data correctly. This effect is independent of the underlying architecture and we show that it can be used to easily detect generated data like deepfakes with up to 100% accuracy on public benchmarks. To overcome this drawback of current generative models, we propose to add a novel spectral regularization term to the training optimization objective. We show that this approach not only allows to train spectral consistent GANs that are avoiding high frequency errors. Also, we show that a correct approximation of the frequency spectrum has positive effects on the training stability and output quality of generative networks.

Image stitching techniques align two images captured at different viewing positions onto a single wider image. When the captured 3D scene is not planar and the camera baseline is large, two images exhibit parallax where the relative positions of scene structures are quite different from each view. The existing image stitching methods often fail to work on the images with large parallax. In this paper, we propose an image stitching algorithm robust to large parallax based on the novel concept of warping residuals. We first estimate multiple homographies and find their inlier feature matches between two images. Then we evaluate warping residual for each feature match with respect to the multiple homographies. To alleviate the parallax artifacts, we partition input images into superpixels and warp each superpixel adaptively according to an optimal homography which is computed by minimizing the error of feature matches weighted by the warping residuals. Experimental results demonstrate that the proposed algorithm provides accurate stitching results for images with large parallax, and outperforms the existing methods qualitatively and quantitatively.

We address anticipation of scene development by forecasting semantic segmentation of future frames. Several previous works approach this problem by F2F (feature-to-feature) forecasting where future features are regressed from observed features. Different from previous work, we consider a novel F2M (feature-to-motion) formulation, which performs the forecast by warping observed features according to regressed feature flow. This formulation models a causal relationship between the past and the future, and regularizes inference by reducing dimensionality of the forecasting target. However, emergence of future scenery which was not visible in observed frames can not be explained by warping. We propose to address this issue by complementing F2M forecasting with the classic F2F approach. We realize this idea as a multi-head F2MF model built atop shared features. Experiments show that the F2M head prevails in static parts of the scene while the F2F head kicks-in to fill-in the novel regions. The proposed F2MF model operates in synergy with correlation features and outperforms all previous approaches both in short-term and mid-term forecast on the Cityscapes dataset.

In this paper, we present a novel regularization mechanism for training deep networks by minimizing the Worse-Case Perturbation (WCP). It is based on the idea that a robust model is least likely to be affected by small perturbations, such that its output decisions should be as stable as possible on both labeled and unlabeled examples. We will consider two forms of WCP regularizations -- additive and DropConnect perturbations, which impose additive noises on network weights, and make structural changes by dropping the network connections, respectively. We will show that the worse cases of both perturbations can be derived by solving respective optimization problems with spectral methods. The WCP can be minimized on both labeled and unlabeled data so that networks can be trained in a semi-supervised fashion. This leads to a novel paradigm of semi-supervised classifiers by stabilizing the predicted outputs in presence of the worse-case perturbations imposed on the network weights and structures.

Understanding of human vision system (HVS) has inspired many computer vision algorithms. Stereo matching, which borrows the idea from human stereopsis, has been extensively studied in the existing literature. However, scant attention has been drawn on a typical scenario where binocular inputs are qualitatively different (e.g., high-res master camera and low-res slave camera in a dual-lens module). Recent advances in human optometry reveal the capability of the human visual system to maintain coarse stereopsis under such visually imbalanced conditions. Bionically aroused, it is natural to question that: do stereo machines share the same capability? In this paper, we carry out a systematic comparison to investigate the effect of various imbalanced conditions on current popular stereo matching algorithms. We show that resembling the human visual system, those algorithms can handle limited degrees of monocular downgrading but also prone to collapses beyond a certain threshold. To avoid such collapse, we propose a solution to recover the stereopsis by a joint guided-view-restoration and stereo-reconstruction framework. We show the superiority of our framework on KITTI dataset and its extension on real-world applications.

Joint understanding of vision and natural language is a challenging problem with a wide range of applications in artificial intelligence. In this work, we focus on integration of video and text for the task of actor and action video segmentation from a sentence. We propose a capsule-based approach which performs pixel-level localization based on a natural language query describing the actor of interest. We encode both the video and textual input in the form of capsules, which provide a more effective representation in comparison with standard convolution based features. Our novel visual-textual routing mechanism allows for the fusion of video and text capsules to successfully localize the actor and action. The existing works on actor-action localization are mainly focused on localization in a single frame instead of the full video. Different from existing works, we propose to perform the localization on all frames of the video. To validate the potential of the proposed network for actor and action video localization, we extend an existing actor-action dataset (A2D) with annotations for all the frames. The experimental evaluation demonstrates the effectiveness of our capsule network for text selective actor and action localization in videos. The proposed method also improves upon the performance of the existing state-of-the art works on single frame-based localization.

Cross-modality semantic matching is a vital task in computer vision and has attracted increasing attention in recent years. Existing methods mainly explore object-based alignment between image objects and text words. In this work, we address this task from two previously-ignored aspects: high-order semantic information (e.g., object-predicate-subject triplet, object-attribute pair) and visual distraction (i.e., despite the high relevance to textual query, images may also contain many prominent distracting objects or visual relations). Specifically, we build scene graphs for both visual and textual modalities. Our technical contributions are two-folds: firstly, we formulate the visual-semantic matching task as an attention-driven cross-modality scene graph matching problem. Graph convolutional networks (GCNs) are used to extract high-order information from two scene graphs. A novel cross-graph attention mechanism is proposed to contextually reweigh graph elements and calculate the inter-graph similarity; Secondly, some top-ranked samples are indeed false matching due to the co-occurrence of both highly-relevant and distracting information. We devise an information-theoretic measure for estimating semantic distraction and re-ranking the initial retrieval results. Comprehensive experiments and ablation studies on two large public datasets (MS-COCO and Flickr30K) demonstrate the superiority of the proposed method and the effectiveness of both high-order attention and distraction.

In this paper we address the problem of visual reaction: the task of interacting with dynamic environments where the changes in the environment are not necessarily caused by the agents itself. Visual reaction entails predicting the future changes in a visual environment and planning accordingly. We study the problem of visual reaction in the context of playing catch with a drone in visually rich synthetic environments. This is a challenging problem since the agent is required to learn (1) how objects with different physical properties and shapes move, (2) what sequence of actions should be taken according to the prediction, (3) how to adjust the actions based on the visual feedback from the dynamic environment (e.g., when objects bouncing off a wall), and (4) how to reason and act with an unexpected state change in a timely manner. We propose a new dataset for this task, which includes 30K throws of 20 types of objects in different directions with different forces. Our results show that our model that integrates a forecaster with a planner outperforms a set of strong baselines that are based on tracking as well as pure model-based and model-free RL baselines. The code and dataset are available at github.com/KuoHaoZeng/Visual_Reaction.

There are thousands of actively spoken languages on Earth, but a single visual world. Grounding in this visual world has the potential to bridge the gap between all these languages. Our goal is to use visual grounding to improve unsupervised word mapping between languages. The key idea is to establish a common visual representation between two languages by learning embeddings from unpaired instructional videos narrated in the native language. Given this shared embedding we demonstrate that (i) we can map words between the languages, particularly the 'visual' words; (ii) that the shared embedding provides a good initialization for existing unsupervised text-based word translation techniques, forming the basis for our proposed hybrid visual-text mapping algorithm, MUVE; and (iii) our approach achieves superior performance by addressing the shortcomings of text-based methods -- it is more robust, handles datasets with less commonality, and is applicable to low-resource languages. We apply these methods to translate words from English to French, Korean, and Japanese -- all without any parallel corpora and simply by watching many videos of people speaking while doing things.

We present a novel unsupervised feature representation learning method, Visual Commonsense Region-based Convolutional Neural Network (VC R-CNN), to serve as an improved visual region encoder for high-level tasks such as captioning and VQA. Given a set of detected object regions in an image (e.g., using Faster R-CNN), like any other unsupervised feature learning methods (e.g., word2vec), the proxy training objective of VC R-CNN is to predict the contextual objects of a region. However, they are fundamentally different: the prediction of VC R-CNN is by using causal intervention: P(Y|do(X)), while others are by using the conventional likelihood: P(Y|X). This is also the core reason why VC R-CNN can learn "sense-making" knowledge like chair can be sat -- while not just "common" co-occurrences such as chair is likely to exist if table is observed. We extensively apply VC R-CNN features in prevailing models of three popular tasks: Image Captioning, VQA, and VCR, and observe consistent performance boosts across them, achieving many new state-of-the-arts.

How can we tell whether an image has been mirrored? While we understand the geometry of mirror reflections very well, less has been said about how it affects distributions of imagery at scale, despite widespread use for data augmentation in computer vision. In this paper, we investigate how the statistics of visual data are changed by reflection. We refer to these changes as "visual chirality," after the concept of geometric chirality---the notion of objects that are distinct from their mirror image. Our analysis of visual chirality reveals surprising results, including low-level chiral signals pervading imagery stemming from image processing in cameras, to the ability to discover visual chirality in images of people and faces. Our work has implications for data augmentation, self-supervised learning, and image forensics.

Vision-Language Navigation (VLN) is a task where an agent learns to navigate following a natural language instruction. The key to this task is to perceive both the visual scene and natural language sequentially. Conventional approaches fully exploit vision and language features in cross-modal grounding. However, the VLN task remains challenging, since previous works have implicitly neglected the rich semantic information contained in environments (such as navigation graphs or sub-trajectory semantics). In this paper, we introduce Auxiliary Reasoning Navigation (AuxRN), a framework with four self-supervised auxiliary reasoning tasks to exploit the additional training signals derived from these semantic information. The auxiliary tasks have four reasoning objectives: explaining the previous actions, evaluating the trajectory consistency, estimating the progress and predict the next direction. As a result, these additional training signals help the agent to acquire knowledge of semantic representations in order to reason about its activities and build a thorough perception of environments. Our experiments demonstrate that auxiliary reasoning tasks improve both the performance of the main task and the model generalizability by a large margin. We further demonstrate empirically that an agent trained with self-supervised auxiliary reasoning tasks substantially outperforms the previous state-of-the-art method, being the best existing approach on the standard benchmark.

Vision-dialog navigation posed as a new holy-grail task in vision-language disciplinary targets at learning an agent endowed with the capability of constant conversation for help with natural language and navigating according to human responses. Besides the common challenges faced in visual language navigation, vision-dialog navigation also requires to handle well with the language intentions of a series of questions about the temporal context from dialogue history and co-reasoning both dialogs and visual scenes. In this paper, we propose the Cross-modal Memory Network (CMN) for remembering and understanding the rich information relevant to historical navigation actions. Our CMN consists of two memory modules, the language memory module (L-mem) and the visual memory module (V-mem). Specifically, L-mem learns latent relationships between the current language interaction and a dialog history by employing a multi-head attention mechanism. V-mem learns to associate the current visual views and the cross-modal memory about the previous navigation actions. The cross-modal memory is generated via a vision-to-language attention and a language-to-vision attention. Benefiting from the collaborative learning of the L-mem and the V-mem, our CMN is able to explore the memory about the decision making of historical navigation actions which is for the current step. Experiments on the CVDN dataset show that our CMN outperforms the previous state-of-the-art model by a significant margin on both seen and unseen environments.

We introduce a new task, Video-and-Language Inference, for joint multimodal understanding of video and text. Given a video clip with aligned subtitles as premise, paired with a natural language hypothesis based on the video content, a model needs to infer whether the hypothesis is entailed or contradicted by the given video clip. A new large-scale dataset, named Violin (VIdeO-and-Language INference), is introduced for this task, which consists of 95,322 video-hypothesis pairs from 15,887 video clips, spanning over 582 hours of video. These video clips contain rich content with diverse temporal dynamics, event shifts, and people interactions, collected from two sources: (i) popular TV shows, and (ii) movie clips from YouTube channels. In order to address our new multimodal inference task, a model is required to possess sophisticated reasoning skills, from surface-level grounding (e.g., identifying objects and characters in the video) to in-depth commonsense reasoning (e.g., inferring causal relations of events in the video). We present a detailed analysis of the dataset and an extensive evaluation over many strong baselines, providing valuable insights on the challenges of this new task.

We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. Our core idea is that inconsistencies in model predictions across viewpoints provide a very reliable measure of uncertainty and encourage the model to perform well irrespective of the viewpoint under which objects are observed. To incorporate this uncertainty measure, we introduce a new viewpoint entropy formulation, which is the basis of our active learning strategy. In addition, we propose uncertainty computations on a superpixel level, which exploits inherently localized signal in the segmentation task, directly lowering the annotation costs. This combination of viewpoint entropy and the use of superpixels allows to efficiently select samples that are highly informative for improving the network. We demonstrate that our proposed active learning strategy not only yields the best-performing models for the same amount of required labeled data, but also significantly reduces labeling effort. For instance, our method achieves 95% of maximum achievable network performance using only 7%, 17%, and 24% labeled data on SceneNet-RGBD, ScanNet, and Matterport3D, respectively. On these datasets, the best state-of-the-art method achieves the same performance with 14%, 27% and 33% labeled data. Finally, we demonstrate that labeling using superpixels yields the same quality of ground-truth compared to labeling whole images, but requires 25% less time.