2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第6页

Divide and Adapt: Active Domain Adaptation via Customized Learning 划分和适应:通过定制学习的主动领域适应

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00739

Duojun Huang, Jichang Li, Weikai Chen, Jun Steed Huang, Z. Chai, Guanbin Li

{"title":"Divide and Adapt: Active Domain Adaptation via Customized Learning","authors":"Duojun Huang, Jichang Li, Weikai Chen, Jun Steed Huang, Z. Chai, Guanbin Li","doi":"10.1109/CVPR52729.2023.00739","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.00739","url":null,"abstract":"Active domain adaptation (ADA) aims to improve the model adaptation performance by incorporating active learning (AL) techniques to label a maximally-informative subset of target samples. Conventional AL methods do not consider the existence of domain shift, and hence, fail to identify the truly valuable samples in the context of domain adaptation. To accommodate active learning and domain adaption, the two naturally different tasks, in a collaborative framework, we advocate that a customized learning strategy for the target data is the key to the success of ADA solutions. We present Divide-and-Adapt (DiaNA), a new ADA framework that partitions the target instances into four categories with stratified transferable properties. With a novel data subdivision protocol based on uncertainty and domainness, DiaNA can accurately recognize the most gainful samples. While sending the informative instances for annotation, DiaNA employs tailored learning strategies for the remaining categories. Furthermore, we propose an informativeness score that unifies the data partitioning criteria. This enables the use of a Gaussian mixture model (GMM) to automatically sample unlabeled data into the proposed four categories. Thanks to the “divide-and-adapt” spirit, DiaNA can handle data with large variations of domain gap. In addition, we show that DiaNA can generalize to different domain adaptation settings, such as unsupervised domain adaptation (UDA), semi-supervised domain adaptation (SSDA), source-free domain adaptation (SFDA), etc.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"461 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125808541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Biomechanics-Guided Facial Action Unit Detection Through Force Modeling 基于力建模的生物力学引导面部动作单元检测

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00840

Zijun Cui, Chenyi Kuang, Tian Gao, Kartik Talamadupula, Qiang Ji

{"title":"Biomechanics-Guided Facial Action Unit Detection Through Force Modeling","authors":"Zijun Cui, Chenyi Kuang, Tian Gao, Kartik Talamadupula, Qiang Ji","doi":"10.1109/CVPR52729.2023.00840","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.00840","url":null,"abstract":"Existing AU detection algorithms are mainly based on appearance information extracted from 2D images, and well-established facial biomechanics that governs 3D facial skin deformation is rarely considered. In this paper, we propose a biomechanics-guided AU detection approach, where facial muscle activation forces are modelled and are employed to predict AU activation. Specifically, our model consists of two branches: 3D physics branch and 2D image branch. In 3D physics branch, we first derive the Euler-Lagrange equation governing facial deformation. The Euler-Lagrange equation represented as an ordinary differential equation (ODE) is embedded into a differentiable ODE solver. Muscle activation forces together with other physics parameters are firstly regressed, and then are utilized to simulate 3D deformation by solving the ODE. By leveraging facial biomechanics, we obtain physically plausible facial muscle activation forces. 2D image branch compensates 3D physics branch by employing additional appearance information from 2D images. Both estimated forces and appearance features are employed for AU detection. The proposed approach achieves competitive AU detection performance on two benchmark datasets. Furthermore, by leveraging biomechanics, our approach achieves outstanding performance with reduced training data.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122253479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

FlowGrad: Controlling the Output of Generative ODEs with Gradients FlowGrad:用梯度控制生成ode的输出

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.02331

Xingchao Liu, Lemeng Wu, Shujian Zhang, Chengyue Gong, Wei Ping, Qiang Liu

{"title":"FlowGrad: Controlling the Output of Generative ODEs with Gradients","authors":"Xingchao Liu, Lemeng Wu, Shujian Zhang, Chengyue Gong, Wei Ping, Qiang Liu","doi":"10.1109/CVPR52729.2023.02331","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.02331","url":null,"abstract":"Generative modeling with ordinary differential equations (ODEs) has achieved fantastic results on a variety of applications. Yet, few works have focused on controlling the generated content of a pre-trained ODE-based generative model. In this paper, we propose to optimize the output of ODE models according to a guidance function to achieve controllable generation. We point out that, the gradients can be efficiently back-propagated from the output to any intermediate time steps on the ODE trajectory, by decomposing the back-propagation and computing vectorJacobian products. To further accelerate the computation of the back-propagation, we propose to use a non-uniform discretization to approximate the ODE trajectory, where we measure how straight the trajectory is and gather the straight parts into one discretization step. This allows us to save ∼ 90% of the back-propagation time with ignorable error. Our framework, named FlowGrad, outperforms the state-of-the-art baselines on text-guided image manipulation. Moreover, FlowGrad enables us to find global semantic directions in frozen ODE-based generative models that can be used to manipulate new images without extra optimization.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127926003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation NewsNet:一种新的分层时间分割数据集

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.01028

Haoqian Wu, Keyun Chen, Haozhe Liu, Mingchen Zhuge, Bing-chuan Li, Ruizhi Qiao, Xiujun Shu, Bei Gan, Liangsheng Xu, Bohan Ren, Mengmeng Xu, Wentian Zhang, Raghavendra Ramachandra, Chia-Wen Lin, Bernard Ghanem

{"title":"NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation","authors":"Haoqian Wu, Keyun Chen, Haozhe Liu, Mingchen Zhuge, Bing-chuan Li, Ruizhi Qiao, Xiujun Shu, Bei Gan, Liangsheng Xu, Bohan Ren, Mengmeng Xu, Wentian Zhang, Raghavendra Ramachandra, Chia-Wen Lin, Bernard Ghanem","doi":"10.1109/CVPR52729.2023.01028","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.01028","url":null,"abstract":"Temporal video segmentation is the get-to- go automatic video analysis, which decomposes a long-form video into smaller components for the following-up understanding tasks. Recent works have studied several levels of granularity to segment a video, such as shot, event, and scene. Those segmentations can help compare the semantics in the corresponding scales, but lack a wider view of larger temporal spans, especially when the video is complex and structured. Therefore, we present two abstractive levels of temporal segmentations and study their hierarchy to the existing fine-grained levels. Accordingly, we collect NewsNet, the largest news video dataset consisting of 1,000 videos in over 900 hours, associated with several tasks for hierarchical temporal video segmentation. Each news video is a collection of stories on different topics, represented as aligned audio, visual, and textual data, along with extensive frame-wise annotations in four granularities. We assert that the study on NewsNet can advance the understanding of complex structured video and benefit more areas such as short-video creation, personalized advertisement, digital instruction, and education. Our dataset and code is publicly available at https://github.com/NewsNet-Benchmark/NewsNet.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127993587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Adaptive Plasticity Improvement for Continual Learning 持续学习的适应性可塑性改进

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00755

Yanyan Liang, Wu-Jun Li

引用次数: 0

Learning Sample Relationship for Exposure Correction 学习曝光校正的样本关系

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00955

Jie Huang, Fengmei Zhao, Man Zhou, Jie Xiao, Naishan Zheng, Kai Zheng, Zhiwei Xiong

{"title":"Learning Sample Relationship for Exposure Correction","authors":"Jie Huang, Fengmei Zhao, Man Zhou, Jie Xiao, Naishan Zheng, Kai Zheng, Zhiwei Xiong","doi":"10.1109/CVPR52729.2023.00955","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.00955","url":null,"abstract":"Exposure correction task aims to correct the underexposure and its adverse overexposure images to the normal exposure in a single network. As well recognized, the optimization flow is the opposite. Despite great advancement, existing exposure correction methods are usually trained with a mini-batch of both underexposure and overexposure mixed samples and have not explored the relationship between them to solve the optimization inconsistency. In this paper, we introduce a new perspective to conjunct their optimization processes by correlating and constraining the relationship of correction procedure in a mini-batch. The core designs of our framework consist of two steps: 1) formulating the exposure relationship of samples across the batch dimension via a context-irrelevant pretext task. 2) delivering the above sample relationship design as the regularization term within the loss function to promote optimization consistency. The proposed sample relationship design as a general term can be easily integrated into existing exposure correction methods without any computational burden in inference time. Extensive experiments over multiple representative exposure correction benchmarks demonstrate consistent performance gains by introducing our sample relationship design.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131365905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 12

STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection STAR损失:减少面部地标检测中的语义歧义

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.01485

Zhengwei Zhou, Huaxia Li, Hong Liu, Na-na Wang, Gang Yu, R. Ji

{"title":"STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection","authors":"Zhengwei Zhou, Huaxia Li, Hong Liu, Na-na Wang, Gang Yu, R. Ji","doi":"10.1109/CVPR52729.2023.01485","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.01485","url":null,"abstract":"Recently, deep learning-based facial landmark detection has achieved significant improvement. However, the semantic ambiguity problem degrades detection performance. Specifically, the semantic ambiguity causes inconsistent annotation and negatively affects the model's convergence, leading to worse accuracy and instability prediction. To solve this problem, we propose a Self-adapTive Ambiguity Reduction (STAR) loss by exploiting the properties of se-mantic ambiguity. We find that semantic ambiguity results in the anisotropic predicted distribution, which inspires us to use predicted distribution to represent semantic ambiguity. Based on this, we design the STAR loss that measures the anisotropism of the predicted distribution. Compared with the standard regression loss, STAR loss is encouraged to be small when the predicted distribution is anisotropic and thus adaptively mitigates the impact of semantic ambiguity. Moreover, we propose two kinds of eigen-value restriction methods that could avoid both distribution's abnormal change and the model's premature convergence. Finally, the comprehensive experiments demonstrate that STAR loss outperforms the state-of-the-art methods on three benchmarks, i.e., COFW, 300W, and WFLW, with negligible computation overhead. Code is at https://github.com/ZhenglinZhou/STAR","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134151367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers 基于视觉变换的高效语义分割的内容感知令牌共享

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.02263

Chenyang Lu, Daan de Geus, Gijs Dubbelman

{"title":"Content-aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers","authors":"Chenyang Lu, Daan de Geus, Gijs Dubbelman","doi":"10.1109/CVPR52729.2023.02263","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.02263","url":null,"abstract":"This paper introduces Content-aware Token Sharing (CTS), a token reduction approach that improves the computational efficiency of semantic segmentation networks that use Vision Transformers (ViTs). Existing works have proposed token reduction approaches to improve the efficiency of ViT-based image classification networks, but these methods are not directly applicable to semantic segmentation, which we address in this work. We observe that, for semantic segmentation, multiple image patches can share a token if they contain the same semantic class, as they contain redundant information. Our approach leverages this by employing an efficient, class-agnostic policy network that predicts if image patches contain the same semantic class, and lets them share a token if they do. With experiments, we explore the critical design choices of CTS and show its effectiveness on the ADE20K, Pascal Context and Cityscapes datasets, various ViT backbones, and different segmentation decoders. With Content-aware Token Sharing, we are able to reduce the number of processed tokens by up to 44%, without diminishing the segmentation quality.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134416482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution 屏幕内容图像超分辨率的b样条纹理系数估计

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00970

B. Pak, Jae-Won Lee, K. Jin

{"title":"B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution","authors":"B. Pak, Jae-Won Lee, K. Jin","doi":"10.1109/CVPR52729.2023.00970","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.00970","url":null,"abstract":"Screen content images (SCIs) include many informative components, e.g., texts and graphics. Such content creates sharp edges or homogeneous areas, making a pixel distribution of SCI different from the natural image. Therefore, we need to properly handle the edges and textures to minimize information distortion of the contents when a display device's resolution differs from SCIs. To achieve this goal, we propose an implicit neural representation using B-splines for screen content image super-resolution (SCI SR) with arbitrary scales. Our method extracts scaling, translating, and smoothing parameters of B-splines. The followed multilayer perceptron (MLP) uses the estimated B-splines to recover high-resolution SCI. Our network outperforms both a transformer-based reconstruction and an implicit Fourier representation method in almost upscaling factor, thanks to the positive constraint and compact support of the B-spline basis. Moreover, our SR results are recognized as correct text letters with the highest confidence by a pre-trained scene text recognition network. Source code is available at https://github.com/ByeongHyunPak/btc.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133890279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning 基于异构图表示学习的组织病理学整张切片图像分析

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.01503

Tsai Hor Chan, Fernando Julio Cendra, Lan Ma, Guosheng Yin, Lequan Yu

{"title":"Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning","authors":"Tsai Hor Chan, Fernando Julio Cendra, Lan Ma, Guosheng Yin, Lequan Yu","doi":"10.1109/CVPR52729.2023.01503","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.01503","url":null,"abstract":"Graph-based methods have been extensively applied to whole slide histopathology image (WSI) analysis due to the advantage of modeling the spatial relationships among different entities. However, most of the existing methods focus on modeling WSIs with homogeneous graphs (e.g., with homogeneous node type). Despite their successes, these works are incapable of mining the complex structural relations between biological entities (e.g., the diverse interaction among different cell types) in the WSI. We propose a novel heterogeneous graph-based framework to leverage the inter-relationships among different types of nuclei for WSI analysis. Specifically, we formulate the WSI as a heterogeneous graph with “nucleus-type” attribute to each node and a semantic similarity attribute to each edge. We then present a new heterogeneous-graph edge attribute transformer (HEAT) to take advantage of the edge and node heterogeneity during massage aggregating. Further, we design a new pseudo-label-based semantic-consistent pooling mechanism to obtain graph-level features, which can mitigate the over-parameterization issue of conventional cluster-based pooling. Additionally, observing the limitations of existing association-based localization methods, we propose a causal-driven approach attributing the contribution of each node to improve the interpretability of our framework. Extensive experiments on three public TCGA benchmark datasets demonstrate that our frame-work outperforms the state-of-the-art methods with considerable margins on various tasks. Our codes are available at https://github.com/HKU-MedAI/WSI-HGNN.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131856159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3