Several approaches have been proposed in recent literature to alleviate the long-tail problem, mainly in object classification tasks. In this paper, we make the first large-scale study concerning the task of Long-Tail Visual Relationship Recognition (LTVRR). LTVRR aims at improving the learning of structured visual relationships that come from the long-tail (e.g.,"rabbit grazing on grass"). In this setup, the subject, relation, and object classes each follow a long-tail distribution. To begin our study and make a future benchmark for the community, we introduce two LTVRR-related benchmarks, dubbed VG8K-LT and GQA-LT, built upon the widely used Visual Genome and GQA datasets. We use these benchmarks to study the performance of several state-of-the-art long-tail models on the LTVRR setup. Lastly, we propose a visiolinguistic hubless (VilHub) loss and a Mixup augmentation technique adapted to LTVRR setup, dubbed as RelMix. Both VilHub and RelMix can be easily integrated on top of existing models and despite being simple, our results show that they can remarkably improve the performance, especially on tail classes. Benchmarks, code, and models have been made available at: https://github.com/Vision-CAIR/LTVRR.
论文检索
输入标题、作者或关键词，从 1,612 篇学术成果中精准定位
Transformers with powerful global relation modeling abilities have been introduced to fundamental computer vision tasks recently. As a typical example, the Vision Transformer (ViT) directly applies a pure transformer architecture on image classification, by simply splitting images into tokens with a fixed length, and employing transformers to learn relations between these tokens. However, such naive tokenization could destruct object structures, assign grids to uninterested regions such as background, and introduce interference signals. To mitigate the above issues, in this paper, we propose an iterative and progressive sampling strategy to locate discriminative regions. At each iteration, embeddings of the current sampling step are fed into a transformer encoder layer, and a group of sampling offsets is predicted to update the sampling locations for the next step. The progressive sampling is differentiable. When combined with the Vision Transformer, the obtained PS-ViT network can adaptively learn where to look. The proposed PS-ViT is both effective and efficient. When trained from scratch on ImageNet, PS-ViT performs 3.8% higher than the vanilla ViT in terms of top-1 accuracy with about 4x fewer parameters and 10x fewer FLOPs. Code is available at https://github.com/yuexy/PS-ViT.
Consistency-Sensitivity Guided Ensemble Black-Box Adversarial Attacks in Low-Dimensional Spaces
PDF ↗Black-box attacks aim to generate adversarial noise tofail the victim deep neural network in the black box. Thecentral task in black-box attack method design is to estimateand characterize the victim model in the high-dimensionalmodel space based on feedback results of queries submittedto the victim network. The central performance goal is tominimize the number of queries needed for successful at-tack. Existing attack methods directly search and refine theadversarial noise in an extremely high-dimensional space,requiring hundreds or even thousands queries to the victimnetwork. To address this challenge, we propose to explore aconsistency and sensitivity guided ensemble attack (CSEA)method in a low-dimensional space. Specifically, we esti-mate the victim model in the black box using a learned lin-ear composition of an ensemble of surrogate models withdiversified network structures. Using random block maskson the input image, these surrogate models jointly constructand submit randomized and sparsified queries to the victimmodel. Based on these query results and guided by a con-sistency constraint, the surrogate models can be trained us-ing a very small number of queries such that their learnedcomposition is able to accurately approximate the victimmodel in the high-dimensional space. The randomized andsparsified queries also provide important information for usto construct an attack sensitivity map for the input image,with which the adversarial attack can be locally refined tofurther increase its success rate. Our extensive experimen-tal results demonstrate that our proposed approach signifi-cantly reduces the number of queries to the victim networkwhile maintaining very high success rates, outperformingexisting black-box attack methods by large margins.
Recent work has made significant progress on using implicit functions, as a continuous representation for 3D rigid object shape reconstruction. However, much less effort has been devoted to modeling general articulated objects. Compared to rigid objects, articulated objects have higher degrees of freedom, which makes it hard to generalize to unseen shapes. To deal with the large shape variance, we introduce Articulated Signed Distance Functions (A-SDF) to represent articulated shapes with a disentangled latent space, where we have separate codes for encoding shape and articulation. With this disentangled continuous representation, we demonstrate that we can control the articulation input and animate unseen instances with unseen joint angles. Furthermore, we propose a Test-Time Adaptation inference algorithm to adjust our model during inference. We demonstrate our model generalize well to out-of-distribution and unseen data, e.g., partial point clouds and real-world depth images.
Images tell powerful stories but cannot always be trusted. Matching images back to trusted sources (attribution) enables users to make a more informed judgment of the images they encounter online. We propose a robust image hashing algorithm to perform such matching. Our hash is sensitive to manipulation of subtle, salient visual details that can substantially change the story told by an image. Yet the hash is invariant to benign transformations (changes in quality, codecs, sizes, shapes, etc.) experienced by images during online redistribution. Our key contribution is OSCAR-Net (Object-centric Scene Graph Attention for Image Attribution Network); a robust image hashing model inspired by recent successes of Transformers in the visual domain. OSCAR-Net constructs a scene graph representation that attends to fine-grained changes of every object's visual appearance and their spatial relationships. The network is trained via contrastive learning on a dataset of original and manipulated images yielding a state of the art image hash for content fingerprinting that scales to millions of images.
Unsupervised image-to-image translation aims at learning the mapping from the source to target domain without using paired images for training. An essential yet restrictive assumption for unsupervised image translation is that the two domains are aligned, e.g., for the selfie2anime task, the anime (selfie) domain must contain only anime (selfie) face images that can be translated to some images in the other domain. Collecting aligned domains can be laborious and needs lots of attention. In this paper, we consider the task of image translation between two unaligned domains, which may arise for various possible reasons. To solve this problem, we propose to select images based on importance reweighting and develop a method to learn the weights and perform translation simultaneously and automatically. We compare the proposed method with state-of-the-art image translation approaches and present qualitative and quantitative results on different tasks with unaligned domains. Extensive empirical evidence demonstrates the usefulness of the proposed problem formulation and the superiority of our method.
Most existing convolution neural network (CNN) based super-resolution (SR) methods generate their paired training dataset by artificially synthesizing low-resolution (LR) images from the high-resolution (HR) ones. However, this dataset preparation strategy harms the application of these CNNs in real-world scenarios due to the inherent domain gap between the training and testing data. A popular attempts towards the challenge is unpaired generative adversarial networks, which generate "real" LR counterparts from real HR images using image-to-image translation and then perform super-resolution from "real" LR->SR. Despite great progress, it is still difficult to synthesize perfect "real" LR images for super-resolution. In this paper, we firstly consider the real-world SR problem from the traditional domain adaptation perspective. We propose a novel unpaired SR training framework based on feature distribution alignment, with which we can obtain degradation-indistinguishable feature maps and then map them to HR images. In order to generate better SR images for target LR domain, we introduce several regularization losses to force the aligned feature to locate around the target domain. Our experiments indicate that our SR network obtains the state-of-the-art performance over both blind and unpaired SR methods on diverse datasets.
High dynamic range (HDR) photography is becoming increasingly popular and available by DSLR and mobile-phone cameras. While deep neural networks (DNN) have greatly impacted other domains of image manipulation, their use for HDR tone-mapping is limited due to the lack of a definite notion of ground-truth solution, which is needed for producing training data. In this paper we describe a new tone-mapping approach guided by the distinct goal of producing low dynamic range (LDR) renditions that best reproduce the visual characteristics of native LDR images. This goal enables the use of an unpaired adversarial training based on unrelated sets of HDR and LDR images, both of which are widely available and easy to acquire. In order to achieve an effective training under this minimal requirements, we introduce the following new steps and components: (i) a range-normalizing pre-process which estimates and applies a different level of curve-based compression, (ii) a loss that preserves the input content while allowing the network to achieve its goal, and (iii) the use of a more concise discriminator network, designed to promote the reproduction of low-level attributes native LDR possess. Evaluation of the resulting network demonstrates its ability to produce photo-realistic artifact-free tone-mapped images, and state-of-the-art performance on different image fidelity indices and visual distances.
Neural Image Compression via Attentional Multi-Scale Back Projection and Frequency Decomposition
PDF ↗In recent years, neural image compression emerges as a rapidly developing topic in computer vision, where the state-of-the-art approaches now exhibit superior compression performance than their conventional counterparts. Despite the great progress, current methods still have limitations in preserving fine spatial details for optimal reconstruction, especially at low compression rates. We make three contributions in tackling this issue. First, we develop a novel back projection method with attentional and multi-scale feature fusion for augmented representation power. Our back projection method recalibrates the current estimation by establishing feedback connections between high-level and low-level attributes in an attentional and discriminative manner. Second, we propose to decompose the input image and separately process the distinct frequency components, whose derived latents are recombined using a novel dual attention module, so that details inside regions of interest could be explicitly manipulated. Third, we propose a novel training scheme for reducing the latent rounding residual. Experimental results show that, when measured in PSNR, our model reduces BD-rate by 9.88% and 10.32% over the state-of-the-art method, and 4.12% and 4.32% over the latest coding standard Versatile Video Coding (VVC) on the Kodak and CLIC2020 Professional Validation dataset, respectively. Our approach also produces more visually pleasant images when optimized for MS-SSIM. The significant improvement upon existing methods shows the effectiveness of our method in preserving and remedying spatial information for enhanced compression quality.
Turn-taking has played an essential role in structuring the regulation of a conversation. The task of identifying the main speaker (who is properly taking his/her turn of speaking) and the interrupters (who are interrupting or reacting to the main speaker's utterances) remains a challenging task. Although some prior methods have partially addressed this task, there still remain some limitations. Firstly, a direct association of Audio and Visual features may limit the correlations to be extracted due to different modalities. Secondly, the relationship across temporal segments helping to maintain the consistency of localization, separation and conversation contexts is not effectively exploited. Finally, the interactions between speakers that usually contain the tracking and anticipatory decisions about transition to a new speaker is usually ignored. Therefore, this work introduces a new Audio-Visual Transformer approach to the problem of localization and highlighting the main speaker in both audio and visual channels of a multi-speaker conversation video in the wild. The proposed method exploits different types of correlations presented in both visual and audio signals. The temporal audio-visual relationships across spatial-temporal space are anticipated and optimized via the self-attention mechanism in a Transformer structure. Moreover, a newly collected dataset is introduced for the main speaker detection. To the best of our knowledge, it is one of the first studies that is able to automatically localize and highlight the main speaker in both visual and audio channels in multi-speaker conversation videos.
Localizing individuals in crowds is more in accordance with the practical demands of subsequent high-level crowd analysis tasks than simply counting. However, existing localization based methods relying on intermediate representations (i.e., density maps or pseudo boxes) serving as learning targets are counter-intuitive and error-prone. In this paper, we propose a purely point-based framework for joint crowd counting and individual localization. For this framework, instead of merely reporting the absolute counting error at image level, we propose a new metric, called density Normalized Average Precision (nAP), to provide more comprehensive and more precise performance evaluation. Moreover, we design an intuitive solution under this framework, which is called Point to Point Network (P2PNet). P2PNet discards superfluous steps and directly predicts a set of point proposals to represent heads in an image, being consistent with the human annotation results. By thorough analysis, we reveal the key step towards implementing such a novel idea is to assign optimal learning targets for these proposals. Therefore, we propose to conduct this crucial association in an one-to-one matching manner using the Hungarian algorithm. The P2PNet not only significantly surpasses state-of-the-art methods on popular counting benchmarks, but also achieves promising localization accuracy. The codes will be available at: https://github.com/TencentYoutuResearch/CrowdCounting-P2PNet.
Preservational Learning Improves Self-Supervised Medical Image Models by Reconstructing Diverse Contexts
PDF ↗Preserving maximal information is the basic principle of designing self-supervised learning methodologies. To reach this goal, contrastive learning adopts an implicit way which is contrasting image pairs. However, we believe it is not fully optimal to simply use the contrastive estimation for preservation. Moreover, it is necessary and complemental to introduce an explicit solution to preserve more information. From this perspective, we introduce Preservational Learning to reconstruct diverse image contexts in order to preserve more information in learned representations. Together with the contrastive loss, we present Preservational Contrastive Representation Learning (PCRL) for learning self-supervised medical representations. PCRL provides very competitive results under the pretraining-finetuning protocol, outperforming both self-supervised and supervised counterparts in 5 classification/segmentation tasks substantially.
We present a novel method for temporal coherent reconstruction and tracking of clothed humans. Given a monocular RGB-D sequence, we learn a person-specific body model which is based on a dynamic surface function network. To this end, we explicitly model the surface of the person using a multi-layer perceptron (MLP) which is embedded into the canonical space of the SMPL body model. With classical forward rendering, the represented surface can be rasterized using the topology of a template mesh. For each surface point of the template mesh, the MLP is evaluated to predict the actual surface location. To handle pose-dependent deformations, the MLP is conditioned on the SMPL pose parameters. We show that this surface representation as well as the pose parameters can be learned in a self-supervised fashion using the principle of analysis-by-synthesis and differentiable rasterization. As a result, we are able to reconstruct a temporally coherent mesh sequence from the input data. The underlying surface representation can be used to synthesize new animations of the reconstructed person including pose-dependent deformations.
Retrieving accurate 3D reconstructions of objects from the way they reflect light is a very challenging task in computer vision. Despite more than four decades since the definition of the Photometric Stereo problem, most of the literature has had limited success when global illumination effects such as cast shadows, self-reflections and ambient light come into play, especially for specular surfaces. Recent approaches have leveraged the capabilities of deep learning in conjunction with computer graphics in order to cope with the need of a vast number of training data to invert the image irradiance equation and retrieve the geometry of the object. However, rendering global illumination effects is a slow process which can limit the amount of training data that can be generated. In this work we propose a novel pixel-wise training procedure for normal prediction by replacing the training data (observation maps) of globally rendered images with independent per-pixel generated data. We show that global physical effects can be approximated on the observation map domain and this simplifies and speeds up the data creation procedure. Our network, PX-NET, achieves state-of-the-art performance compared to other pixelwise methods on synthetic datasets, as well as the DiLiGenT real dataset on both dense and sparse light settings.
Predicting the future frames of a video is a challenging task, in part due to the underlying stochastic real-world phenomena. Prior approaches to solve this task typically estimate a latent prior characterizing this stochasticity, however do not account for the predictive uncertainty of the (deep learning) model. Such approaches often derive the training signal from the mean-squared error (MSE) between the generated frame and the ground truth, which can lead to sub-optimal training, especially when the predictive uncertainty is high. Towards this end, we introduce Neural Uncertainty Quantifier (NUQ) - a stochastic quantification of the model's predictive uncertainty, and use it to weigh the MSE loss. We propose a hierarchical, variational framework to derive NUQ in a principled manner using a deep, Bayesian graphical model. Our experiments on three benchmark stochastic video prediction datasets show that our proposed framework trains more effectively compared to the state-of-the-art models (especially when the training sets are small), while demonstrating better video generation quality and diversity against several evaluation metrics.
Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world performance. We propose to use self-supervised monocular depth estimation as a proxy task to bridge this gap and improve sim-to-real unsupervised domain adaptation (UDA). Our Geometric Unsupervised Domain Adaptation method (GUDA) learns a domain-invariant representation via a multi-task objective combining synthetic semantic supervision with real-world geometric constraints on videos. GUDA establishes a new state of the art in UDA for semantic segmentation on three benchmarks, outperforming methods that use domain adversarial learning, self-training, or other self-supervised proxy tasks. Furthermore, we show that our method scales well with the quality and quantity of synthetic data while also improving depth prediction.
Image matting refers to the estimation of the opacity of foreground objects. It requires correct contours and fine details of foreground objects for the matting results. To better accomplish human image matting tasks, we propose the Cascade Image Matting Network with Deformable Graph Refinement(CasDGR), which can automatically predict precise alpha mattes from single human images without any additional inputs. We adopt a network cascade architecture to perform matting from low-to-high resolution, which corresponds to coarse-to-fine optimization. We also introduce the Deformable Graph Refinement (DGR) module based on graph neural networks (GNNs) to overcome the limitations of convolutional neural networks (CNNs). The DGR module can effectively capture long-range relations and obtain more global and local information to help produce finer alpha mattes. We also reduce the computation complexity of the DGR module by dynamically predicting the neighbors and apply DGR module to higher-resolution features. Experimental results demonstrate the ability of our CasDGR to achieve state-of-the-art performance on synthetic datasets and produce good results on real human images.
Few-Shot Learning (FSL) aims at classifying samples into new unseen classes with only a handful of labeled samples available. However, most of the existing methods are based on the image-level pooled representation, yet ignore considerable local clues that are transferable across tasks. To address this issue, we propose an end-to-end Task-aware Part Mining Network (TPMN) by integrating an automatic part mining process into the metric-based model for FSL. The proposed TPMN model enjoys several merits. First, we design a meta filter learner to generate task-aware part filters based on the task embedding in a meta-learning way. The task-aware part filters can adapt to any individual task and automatically mine task-related local parts even for an unseen task. Second, an adaptive importance generator is proposed to identify key local parts and assign adaptive importance weights to different parts. To the best of our knowledge, this is the first work to automatically exploit the task-aware local parts in a meta-learning way for FSL. Extensive experimental results on four standard benchmarks demonstrate that the proposed model performs favorably against state-of-the-art FSL methods.
Vision-and-language (V&L) reasoning necessitates perception of visual concepts such as objects and actions, understanding semantics and language grounding, and reasoning about the interplay between the two modalities. One crucial aspect of visual reasoning is spatial understanding, which involves understanding relative locations of objects, i.e. implicitly learning the geometry of the scene. In this work, we evaluate the faithfulness of V&L models to such geometric understanding, by formulating the prediction of pair-wise relative locations of objects as a classification as well as a regression task. Our findings suggest that state-of-the-art transformer-based V&L models lack sufficient abilities to excel at this task. Motivated by this, we design two objectives as proxies for 3D spatial reasoning (SR) -- object centroid estimation, and relative position estimation, and train V&L with weak supervision from off-the-shelf depth estimators. This leads to considerable improvements in accuracy for the "GQA" visual question answering challenge (in fully supervised, few-shot, and O.O.D settings) as well as improvements in relative spatial reasoning. Code and data will be released here.
Current state-of-the-art object detection and segmentation methods work well under the closed-world assumption. This closed-world setting assumes that the list of object categories is available during training and deployment. However, many real-world applications require detecting or segmenting novel objects, i.e., object categories never seen during training. In this paper, we present, UVO (Unidentified Video Objects), a new benchmark for open-world class-agnostic object segmentation in videos. Besides shifting the focus to the open-world setup, UVO is significantly larger, providing approximately 6 times more videos compared with DAVIS, and 7 times more mask (instance) annotations per video compared with YouTube-VO(I)S. UVO is also more challenging as it includes many videos with crowded scenes and complex background motions. We also demonstrated that UVO can be used for other applications, such as object tracking and super-voxel segmentation. We believe that UVO is a versatile testbed for researchers to develop novel approaches for open-world class-agnostic object segmentation, and inspires new research directions towards a more comprehensive video understanding beyond classification and detection.