CVPR 2022 论文列表

Unsupervised domain adaptive video action recognition aims to recognize actions of a target domain using a model trained with only out-of-domain (source) annotations. The inherent complexity of videos makes this task challenging but also provides ground for leveraging multi-modal inputs (e.g., RGB, Flow, Audio). Most previous works utilize the multi-modal information by either aligning each modality individually or learning representation via cross-modal self-supervision. Different from previous works, we find that the cross-domain alignment can be more effectively done by using cross-modal interaction first. Cross-modal knowledge interaction allows other modalities to supplement missing transferable information because of the cross-modal complementarity. Also, the most transferable aspects of data can be highlighted using cross-modal consensus. In this work, we present a novel model that jointly considers these two characteristics for domain adaptive action recognition. We achieve this by implementing two modules, where the first module exchanges complementary transferable information across modalities through the semantic space, and the second module finds the most transferable spatial region based on the consensus of all modalities. Extensive experiments validate that our proposed method can significantly outperform the state-of-the-art methods on multiple benchmark datasets, including the complex fine-grained dataset EPIC-Kitchens-100.

The target of automatic video summarization is to create a short skim of the original long video while preserving the major content/events. There is a growing interest in the integration of user queries into video summarization or query-driven video summarization. This video summarization method predicts a concise synopsis of the original video based on the user query, which is commonly represented by the input text. However, two inherent problems exist in this query-driven way. First, the text query might not be enough to describe the exact and diverse needs of the user. Second, the user cannot edit once the summaries are produced, while we assume the needs of the user should be subtle and need to be adjusted interactively. To solve these two problems, we propose IntentVizor, an interactive video summarization framework guided by generic multi-modality queries. The input query that describes the user's needs are not limited to text but also the video snippets. We further represent these multi-modality finer-grained queries as user 'intent', which is interpretable, interactable, editable, and can better quantify the user's needs. In this paper, we use a set of the proposed intents to represent the user query and design a new interactive visual analytic interface. Users can interactively control and adjust these mixed-initiative intents to obtain a more satisfying summary through the interface. Also, to improve the summarization quality via video understanding, a novel Granularity-Scalable Ego-Graph Convolutional Networks (GSE-GCN) is proposed. We conduct our experiments on two benchmark datasets. Comparisons with the state-of-the-art methods verify the effectiveness of the proposed framework. Code and dataset are available at https://github.com/jnzs1836/intent-vizor.

We introduce the integrative task of few-shot classification and segmentation (FS-CS) that aims to both classify and segment target objects in a query image when the target classes are given with a few examples. This task combines two conventional few-shot learning problems, few-shot classification and segmentation. FS-CS generalizes them to more realistic episodes with arbitrary image pairs, where each target class may or may not be present in the query. To address the task, we propose the integrative few-shot learning (iFSL) framework for FS-CS, which trains a learner to construct class-wise foreground maps for multi-label classification and pixel-wise segmentation. We also develop an effective iFSL model, attentive squeeze network (ASNet), that leverages deep semantic correlation and global self-attention to produce reliable foreground maps. In experiments, the proposed method shows promising performance on the FS-CS task and also achieves the state of the art on standard few-shot segmentation benchmarks

In this paper, we introduce a new dataset, named InstaOrder, that can be used to understand the spatial relationships of instances in a 3D space. The dataset consists of 2.9M annotations of geometric orderings for class-labeled instances in 101K natural scenes. The scenes were annotated by 3,659 crowd-workers regarding (1) occlusion order that identifies occluder/occludee and (2) depth order that describes ordinal relations that consider relative distance from the camera. The dataset provides joint annotation of two kinds of orderings for the same instances, and we discover that the occlusion order and depth order are complementary. We also introduce a geometric order prediction network called InstaOrderNet, which is superior to state-of-the-art approaches. Moreover, we propose a dense depth prediction network called InstaDepthNet that uses auxiliary geometric order loss to boost the accuracy of the state-of-the-art depth prediction approach, MiDaS [54].

In label-noise learning, estimating the transition matrix has attracted more and more attention as the matrix plays an important role in building statistically consistent classifiers. However, it is very challenging to estimate the transition matrix T(x), where T(x) denotes the instance, because it is unidentifiable under the instance-dependent noise (IDN). To address this problem, we have noticed that, there are psychological and physiological evidences showing that we humans are more likely to annotate instances of similar appearances to the same classes, and thus poor-quality or ambiguous instances of similar appearances are easier to be mislabeled to the correlated or same noisy classes. Therefore, we propose assumption on the geometry of T(x) that "the closer two instances are, the more similar their corresponding transition matrices should be". More specifically, we formulate above assumption into the manifold embedding, to effectively reduce the degree of freedom of T(x) and make it stably estimable in practice. This proposed manifold-regularized technique works by directly reducing the estimation error without hurting the approximation error about the estimation problem of T(x) Experimental evaluations on four synthetic and two real-world datasets demonstrate our method is superior to state-of-the-art approaches for label-noise learning under the challenging IDN.

Quantization is an effective way to reduce the memory and computational costs of deep neural networks in which the full-precision weights and activations are represented using low-bit values. The bit-width for each layer in most of existing quantization methods is static, i.e., the same for all samples in the given dataset. However, natural images are of huge diversity with abundant content and using such a universal quantization configuration for all samples is not an optimal strategy. In this paper, we present to conduct the low-bit quantization for each image individually, and develop a dynamic quantization scheme for exploring their optimal bit-widths. To this end, a lightweight bit-controller is established and trained jointly with the given neural network to be quantized. During inference, the quantization configuration for an arbitrary image will be determined by the bit-widths generated by the controller, e.g., an image with simple texture will be allocated with lower bits and computational complexity and vice versa. Experimental results conducted on benchmarks demonstrate the effectiveness of the proposed dynamic quantization method for achieving state-of-art performance in terms of accuracy and computational complexity. The code will be available at https://github.com/huawei-noah/Efficient-Computing and https://gitee.com/mindspore/models/tree/master/research/cv/DynamicQuant.

In this paper, we present an end-to-end instance segmentation method that regresses a polygonal boundary for each object instance. This sparse, vectorized boundary representation for objects, while attractive in many downstream computer vision tasks, quickly runs into issues of parity that need to be addressed: parity in supervision and parity in performance when compared to existing pixel-based methods. This is due in part to object instances being annotated with ground-truth in the form of polygonal boundaries or segmentation masks, yet being evaluated in a convenient manner using only segmentation masks. Our method, named BoundaryFormer, is a Transformer based architecture that directly predicts polygons yet uses instance mask segmentations as the ground-truth supervision for computing the loss. We achieve this by developing an end-to-end differentiable model that solely relies on supervision within the mask space through differentiable rasterization. BoundaryFormer matches or surpasses the Mask R-CNN method in terms of instance segmentation quality on both COCO and Cityscapes while exhibiting significantly better transferability across datasets.

We present a novel Transformer-based network architecture for instance-aware image-to-image translation, dubbed InstaFormer, to effectively integrate global- and instance-level information. By considering extracted content features from an image as tokens, our networks discover global consensus of content features by considering context information through a self-attention module in Transformers. By augmenting such tokens with an instance-level feature extracted from the content feature with respect to bounding box information, our framework is capable of learning an interaction between object instances and the global image, thus boosting the instance-awareness. We replace layer normalization (LayerNorm) in standard Transformers with adaptive instance normalization (AdaIN) to enable a multi-modal translation with style codes. In addition, to improve the instance-awareness and translation quality at object regions, we present an instance-level content contrastive loss defined between input and translated image. We conduct experiments to demonstrate the effectiveness of our InstaFormer over the latest methods and provide extensive ablation studies.

While GANs can produce photo-realistic images in ideal conditions for certain domains, the generation of full-body human images remains difficult due to the diversity of identities, hairstyles, clothing, and the variance in pose. Instead of modeling this complex domain with a single GAN, we propose a novel method to combine multiple pretrained GANs, where one GAN generates a global canvas (e.g., human body) and a set of specialized GANs, or insets, focus on different parts (e.g., faces, shoes) that can be seamlessly inserted onto the global canvas. We model the problem as jointly exploring the respective latent spaces such that the generated images can be combined, by inserting the parts from the specialized generators onto the global canvas, without introducing seams. We demonstrate the setup by combining a full body GAN with a dedicated high-quality face GAN to produce plausible-looking humans. We evaluate our results with quantitative metrics and user studies.

Much of the recent progress in 3D vision has been driven by the development of specialized architectures that incorporate geometrical inductive biases. In this paper we tackle 3D reconstruction using a domain agnostic architecture and study how instead to inject the same type of inductive biases directly as extra inputs to the model. This approach makes it possible to apply existing general models, such as Perceivers, on this rich domain, without the need for architectural changes, while simultaneously maintaining data efficiency of bespoke models. In particular we study how to encode cameras, projective ray incidence and epipolar geometry as model inputs, and demonstrate competitive multi-view depth estimation performance on multiple benchmarks.

Tremendous progress has been made in recent years in developing better image captioning models, yet most of them rely on a separate object detector to extract regional features. Recent vision-language studies are shifting towards the detector-free trend by leveraging grid representations for more flexible model training and faster inference speed. However, such development is primarily focused on image understanding tasks, and remains less investigated for the caption generation task. In this paper, we are concerned with a better-performing detector-free image captioning model, and propose a pure vision transformer-based image captioning model, dubbed as ViTCAP, in which grid representations are used without extracting the regional features. For improved performance, we introduce a novel Concept Token Network (CTN) to predict the semantic concepts and then incorporate them into the end-to-end captioning. In particular, the CTN is built on the basis of a vision transformer and is designed to predict the concept tokens through a classification task, from which the rich semantic information contained greatly benefits the captioning task. Compared with the previous detector-based models, ViTCAP drastically simplifies the architectures and at the same time achieves competitive performance on various challenging image captioning datasets. In particular, ViTCAP reaches 138.1 CIDEr scores on COCO-caption Karpathy-split, 93.8 and 108.6 CIDEr scores on nocaps and Google-CC captioning datasets, respectively.

We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural implicit representation. The proposed approach minimizes potential reconstruction inconsistency that happens due to insufficient viewpoints by imposing the entropy constraint of the density in each ray. In addition, to alleviate the potential degenerate issue when all training images are acquired from almost redundant viewpoints, we further incorporate the spatially smoothness constraint into the estimated images by restricting information gains from a pair of rays with slightly different viewpoints. The main idea of our algorithm is to make reconstructed scenes compact along individual rays and consistent across rays in the neighborhood. The proposed regularizers can be plugged into most of existing neural volume rendering techniques based on NeRF in a straightforward way. Despite its simplicity, we achieve consistently improved performance compared to existing neural view synthesis methods by large margins on multiple standard benchmarks.

Human skeleton-based action recognition offers a valuable means to understand the intricacies of human behavior because it can handle the complex relationships between physical constraints and intention. Although several studies have focused on encoding a skeleton, less attention has been paid to embed this information into the latent representations of human action. InfoGCN proposes a learning framework for action recognition combining a novel learning objective and an encoding method. First, we design an information bottleneck-based learning objective to guide the model to learn informative but compact latent representations. To provide discriminative information for classifying action, we introduce attention-based graph convolution that captures the context-dependent intrinsic topology of human action. In addition, we present a multi-modal representation of the skeleton using the relative position of joints, designed to provide complementary spatial information for joints. InfoGCN surpasses the known state-of-the-art on multiple skeleton-based action recognition benchmarks with the accuracy of 93.0% on NTU RGB+D 60 cross-subject split, 89.8% on NTU RGB+D 120 cross-subject split, and 97.0% on NW-UCLA.

Physical objects have inertia, which resists changes in the velocity and motion direction. Inspired by this, we introduce inertia prior that optical flow, which reflects object motion in a local temporal window, keeps unchanged in the adjacent preceding or subsequent frame. We propose a flow completion network to align and aggregate flow features from the consecutive flow sequences based on the inertia prior. The corrupted flows are completed under the supervision of customized losses on reconstruction, flow smoothness, and consistent ternary census transform. The completed flows with high fidelity give rise to significant improvement on the video inpainting quality. Nevertheless, the existing flow-guided cross-frame warping methods fail to consider the lightening and sharpness variation across video frames, which leads to spatial incoherence after warping from other frames. To alleviate such problem, we propose the Adaptive Style Fusion Network (ASFN), which utilizes the style information extracted from the valid regions to guide the gradient refinement in the warped regions. Moreover, we design a data simulation pipeline to reduce the training difficulty of ASFN. Extensive experiments show the superiority of our method against the state-of-the-art methods quantitatively and qualitatively. The project page is at https://github.com/hitachinsk/ISVI

We propose a novel style transfer method to quickly create a new visual product with a nice appearance for industrial designers' reference. Given a source product, a target product, and an art style image, our method produces a neural warping field that warps the source shape to imitate the geometric style of the target and a neural texture transformation network that transfers the artistic style to the warped source product. Our model, Industrial Style Transfer (InST), consists of large-scale geometric warping (LGW) and interest-consistency texture transfer (ICTT). LGW aims to explore an unsupervised transformation between the shape masks of the source and target products for fitting large-scale shape warping. Furthermore, we introduce a mask smoothness regularization term to prevent the abrupt changes of the details of the source product. ICTT introduces an interest regularization term to maintain important contents of the warped product when it is stylized by using the art style image. Extensive experimental results demonstrate that InST achieves state-of-the-art performance on multiple visual product design tasks, e.g., companies' snail logos and classical bottles (please see Fig. 1). To the best of our knowledge, we are the first to extend the neural style transfer method to create industrial product appearances. Code is available at https://jcyang98.github.io/InST/home.html

Image inpainting has made significant advances in recent years. However, it is still challenging to recover corrupted images with both vivid textures and reasonable structures. Some specific methods can only tackle regular textures while losing holistic structures due to the limited receptive fields of convolutional neural networks (CNNs). On the other hand, attention-based models can learn better long-range dependency for the structure recovery, but they are limited by the heavy computation for inference with large image sizes. To address these issues, we propose to leverage an additional structure restorer to facilitate the image inpainting incrementally. The proposed model restores holistic image structures with a powerful attention-based transformer model in a fixed low-resolution sketch space. Such a grayscale space is easy to be upsampled to larger scales to convey correct structural information. Our structure restorer can be integrated with other pretrained inpainting models efficiently with the zero-initialized residual addition. Furthermore, a masking positional encoding strategy is utilized to improve the performance of the proposed model with large irregular masks. Extensive experiments on various datasets validate the efficacy of our model compared with other competitors.

Although existing semantic segmentation approaches achieve impressive results, they still struggle to update their models incrementally as new categories are uncovered. Furthermore, pixel-by-pixel annotations are expensive and time-consuming. This paper proposes a novel framework for Weakly Incremental Learning for Semantic Segmentation, that aims at learning to segment new classes from cheap and largely available image-level labels. As opposed to existing approaches, that need to generate pseudo-labels offline, we use a localizer, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally. We cope with the inherent noise in the process by using soft-labels generated by the localizer. We demonstrate the effectiveness of our approach on the Pascal VOC and COCO datasets, outperforming offline weakly-supervised methods and obtaining results comparable with incremental learning methods with full supervision.

Due to the constraints of the imaging device and high cost in operation time, computer tomography (CT) scans are usually acquired with low within-slice resolution. Improving the inter-slice resolution is beneficial to the disease diagnosis for both human experts and computer-aided systems. To this end, this paper builds a novel medical slice synthesis to increase the inter-slice resolution. Considering that the ground-truth intermediate medical slices are always absent in clinical practice, we introduce the incremental cross-view mutual distillation strategy to accomplish this task in the self-supervised learning manner. Specifically, we model this problem from three different views: slice-wise interpolation from axial view and pixel-wise interpolation from coronal and sagittal views. Under this circumstance, the models learned from different views can distill valuable knowledge to guide the learning processes of each other. We can repeat this process to make the models synthesize intermediate slice data with increasing between-slice resolution. To demonstrate the effectiveness of the proposed approach, we conduct comprehensive experiments on a large-scale CT dataset. Quantitative and qualitative comparison results show that our method outperforms state-of-the-art algorithms by clear margins.

Full-reference (FR) image quality assessment (IQA) evaluates the visual quality of a distorted image by measuring its perceptual difference with pristine-quality reference, and has been widely used in low level vision tasks. Pairwise labeled data with mean opinion score (MOS) are required in training FR-IQA model, but is time-consuming and cumbersome to collect. In contrast, unlabeled data can be easily collected from an image degradation or restoration process, making it encouraging to exploit unlabeled training data to boost FR-IQA performance. Moreover, due to the distribution inconsistency between labeled and unlabeled data, outliers may occur in unlabeled data, further increasing the training difficulty. In this paper, we suggest to incorporate semi-supervised and positive-unlabeled (PU) learning for exploiting unlabeled data while mitigating the adverse effect of outliers. Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i.e., outliers) from unlabeled data. Semi-supervised learning (SSL) is further deployed to exploit positive unlabeled data by dynamically generating pseudo-MOS. We adopt a dual-branch network including reference and distortion branches. Furthermore, spatial attention is introduced in the reference branch to concentrate more on the informative regions, and sliced Wasserstein distance is used for robust difference map computation to address the misalignment issues caused by images recovered by GAN models. Extensive experiments show that our method performs favorably against state-of-the-arts on the benchmark datasets PIPAL, KADID-10k, TID2013, LIVE and CSIQ.