2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第8页

Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation 匹配是不够的:一个两阶段框架的类别不可知论姿态估计

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00706

Min Shi, Zihao Huang, Xianzheng Ma, Xiaowei Hu, Zhiguo Cao

{"title":"Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation","authors":"Min Shi, Zihao Huang, Xianzheng Ma, Xiaowei Hu, Zhiguo Cao","doi":"10.1109/CVPR52729.2023.00706","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.00706","url":null,"abstract":"Category-agnostic pose estimation (CAPE) aims to predict keypoints for arbitrary categories given support images with keypoint annotations. Existing approaches match the keypoints across the image for localization. However, such a one-stage matching paradigm shows inferior accuracy: the prediction heavily relies on the matching results, which can be noisy due to the open set nature in CAPE. For example, two mirror-symmetric keypoints (e.g., left and right eyes) in the query image can both trigger high similarity on certain support keypoints (eyes), which leads to duplicated or opposite predictions. To calibrate the inaccurate matching results, we introduce a two-stage framework, where matched keypoints from the first stage are viewed as similarity-aware position proposals. Then, the model learns to fetch relevant features to correct the initial proposals in the second stage. We instantiate the framework with a transformer model tailored for CAPE. The transformer encoder incorporates specific designs to improve the representation and similarity modeling in the first matching stage. In the second stage, similarity-aware proposals are packed as queries in the decoder for refinement via cross-attention. Our method surpasses the previous best approach by large margins on CAPE benchmark MP-100 on both accuracy and efficiency. Code available at github.com/flyinglynx/CapeFormer","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"44 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":"132263458","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

Mask-Guided Matting in the Wild 面具引导的野外铺地

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00198

KwanYong Park, Sanghyun Woo, Seoung Wug Oh, In-So Kweon, Joon-Young Lee

引用次数: 0

Balancing Logit Variation for Long-Tailed Semantic Segmentation 平衡Logit变异的长尾语义分割

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.01874

Yuchao Wang, Jingjing Fei, Haochen Wang, Wei Li, Tianpeng Bao, Liwei Wu, Rui Zhao, Yujun Shen

{"title":"Balancing Logit Variation for Long-Tailed Semantic Segmentation","authors":"Yuchao Wang, Jingjing Fei, Haochen Wang, Wei Li, Tianpeng Bao, Liwei Wu, Rui Zhao, Yujun Shen","doi":"10.1109/CVPR52729.2023.01874","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.01874","url":null,"abstract":"Semantic segmentation usually suffers from a long-tail data distribution. Due to the imbalanced number of samples across categories, the features of those tail classes may get squeezed into a narrow area in the feature space. Towards a balanced feature distribution, we introduce category-wise variation into the network predictions in the training phase such that an instance is no longer projected to a feature point, but a small region instead. Such a perturbation is highly dependent on the category scale, which appears as assigning smaller variation to head classes and larger variation to tail classes. In this way, we manage to close the gap between the feature areas of different categories, resulting in a more balanced representation. It is note-worthy that the introduced variation is discarded at the inference stage to facilitate a confident prediction. Although with an embarrassingly simple implementation, our method manifests itself in strong generalizability to various datasets and task settings. Extensive experiments suggest that our plug-in design lends itself well to a range of state-of-the-art approaches and boosts the performance on top of them.11Code: https://github.com/grantword8/BLV.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"518 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":"127824452","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

Balanced Energy Regularization Loss for Out-of-distribution Detection 非分布检测中的平衡能量正则化损失

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.01506

Hyunjun Choi, Hawook Jeong, Jin Young Choi

引用次数: 1

Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery 引导你自己的先验:走向分布不可知论的新类发现

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00337

Muli Yang, Liancheng Wang, Cheng Deng, Hanwang Zhang

{"title":"Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery","authors":"Muli Yang, Liancheng Wang, Cheng Deng, Hanwang Zhang","doi":"10.1109/CVPR52729.2023.00337","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.00337","url":null,"abstract":"Novel Class Discovery (NCD) aims to discover unknown classes without any annotation, by exploiting the transferable knowledge already learned from a base set of known classes. Existing works hold an impractical assumption that the novel class distribution prior is uniform, yet neglect the imbalanced nature of real-world data. In this paper, we relax this assumption by proposing a new challenging task: distribution-agnostic NCD, which allows data drawn from arbitrary unknown class distributions and thus renders existing methods useless or even harmful. We tackle this challenge by proposing a new method, dubbed “Boot-strapping Your Own Prior (BYOP)”, which iteratively estimates the class prior based on the model prediction it-self. At each iteration, we devise a dynamic temperature technique that better estimates the class prior by encouraging sharper predictions for less-confident samples. Thus, BYOP obtains more accurate pseudo-labels for the novel samples, which are beneficial for the next training iteration. Extensive experiments show that existing methods suffer from imbalanced class distributions, while BYOp11Code: https://github.com/muliyangm/BYOP. out-performs them by clear margins, demonstrating its effectiveness across various distribution scenarios.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"3 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":"131674883","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: 6

Learning Analytical Posterior Probability for Human Mesh Recovery 学习分析后验概率人体网格恢复

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00848

Qi Fang, Kang Chen, Yinghui Fan, Qing Shuai, Jiefeng Li, Weidong Zhang

引用次数: 4

Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model 方便:迈向高保真3D手形状和外观模型

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00453

Rolandos Alexandros Potamias, Stylianos Ploumpis, Stylianos Moschoglou, Vasileios Triantafyllou, S. Zafeiriou

{"title":"Handy: Towards a High Fidelity 3D Hand Shape and Appearance Model","authors":"Rolandos Alexandros Potamias, Stylianos Ploumpis, Stylianos Moschoglou, Vasileios Triantafyllou, S. Zafeiriou","doi":"10.1109/CVPR52729.2023.00453","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.00453","url":null,"abstract":"Over the last few years, with the advent of virtual and augmented reality, an enormous amount of research has been focused on modeling, tracking and reconstructing human hands. Given their power to express human behavior, hands have been a very important, but challenging component of the human body. Currently, most of the state-of-the-art reconstruction and pose estimation methods rely on the low polygon MANO model. Apart from its low polygon count, MANO model was trained with only 31 adult subjects, which not only limits its expressive power but also imposes unnecessary shape reconstruction constraints on pose estimation methods. Moreover, hand appearance remains almost unexplored and neglected from the majority of hand reconstruction methods. In this work, we propose “Handy”, a large-scale model of the human hand, modeling both shape and appearance composed of over 1200 subjects which we make publicly available for the benefit of the research community. In contrast to current models, our proposed hand model was trained on a dataset with large diversity in age, gender, and ethnicity, which tackles the limitations of MANO and accurately reconstructs out-of-distribution samples. In order to create a high quality texture model, we trained a powerful GAN, which preserves high frequency details and is able to generate high resolution hand textures. To showcase the capabilities of the proposed model, we built a synthetic dataset of textured hands and trained a hand pose estimation network to reconstruct both the shape and appearance from single images. As it is demonstrated in an extensive series of quantitative as well as qualitative experiments, our model proves to be robust against the state-of-the-art and realistically captures the 3D hand shape and pose along with a high frequency detailed texture even in adverse “in-the-wild” conditions.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"331 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":"115459655","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: 0

ScaleFL: Resource-Adaptive Federated Learning with Heterogeneous Clients 基于异构客户端的资源自适应联邦学习

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.02350

Fatih Ilhan, Gong Su, Ling Liu

{"title":"ScaleFL: Resource-Adaptive Federated Learning with Heterogeneous Clients","authors":"Fatih Ilhan, Gong Su, Ling Liu","doi":"10.1109/CVPR52729.2023.02350","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.02350","url":null,"abstract":"Federated learning (FL) is an attractive distributed learning paradigm supporting real-time continuous learning and client privacy by default. In most FL approaches, all edge clients are assumed to have sufficient computation capabilities to participate in the learning of a deep neural network (DNN) model. However, in real-life applications, some clients may have severely limited resources and can only train a much smaller local model. This paper presents ScaleFL, a novel FL approach with two distinctive mechanisms to handle resource heterogeneity and provide an equitable FL framework for all clients. First, ScaleFL adaptively scales down the DNN model along width and depth dimensions by leveraging early exits to find the best-fit models for resource-aware local training on distributed clients. In this way, ScaleFL provides an efficient balance of preserving basic and complex features in local model splits with various sizes for joint training while enabling fast inference for model deployment. Second, ScaleFL utilizes self-distillation among exit predictions during training to improve aggregation through knowledge transfer among subnetworks. We conduct extensive experiments on benchmark CV (CIFAR-10/100, ImageNet) and NLP datasets (SST-2, AgNews). We demonstrate that ScaleFL outperforms existing representative heterogeneous FL approaches in terms of global/local model performance and provides inference efficiency, with up to 2x latency and 4x model size reduction with negligible performance drop below 2%.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"77 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":"115654545","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: 4

You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement 在基于视黄醇的微光图像增强中，您不需要额外的先验或正则器

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.01738

Huiyuan Fu, Wenkai Zheng, Xiangyu Meng, X. Wang, Chuanming Wang, Huadong Ma

{"title":"You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement","authors":"Huiyuan Fu, Wenkai Zheng, Xiangyu Meng, X. Wang, Chuanming Wang, Huadong Ma","doi":"10.1109/CVPR52729.2023.01738","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.01738","url":null,"abstract":"Images captured in low-light conditions often suffer from significant quality degradation. Recent works have built a large variety of deep Retinex-based networks to enhance low-light images. The Retinex-based methods require decomposing the image into reflectance and illumination components, which is a highly ill-posed problem and there is no available ground truth. Previous works addressed this problem by imposing some additional priors or regularizers. However, finding an effective prior or regularizer that can be applied in various scenes is challenging, and the performance of the model suffers from too many additional constraints. We propose a contrastive learning method and a self-knowledge distillation method for Retinex decomposition that allow training our Retinex-based model without elaborate hand-crafted regularization functions. Rather than estimating reflectance and illuminance images and representing the final images as their element-wise products as in previous works, our regularizer-free Retinex decomposition and synthesis network (RFR) extracts reflectance and illuminance features and synthesizes them end-to-end. In addition, we propose a loss function for contrastive learning and a progressive learning strategy for self-knowledge distillation. Extensive experimental results demonstrate that our proposed methods can achieve superior performance compared with state-of-the-art approaches.","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":"115884416","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

OSAN: A One-Stage Alignment Network to Unify Multimodal Alignment and Unsupervised Domain Adaptation 一种统一多模态对齐和无监督域自适应的单阶段对齐网络

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2023-06-01 DOI: 10.1109/CVPR52729.2023.00346

Ye Liu, Lingfeng Qiao, Chang-Tien Lu, Di Yin, Chen Lin, Haoyuan Peng, Bo Ren

{"title":"OSAN: A One-Stage Alignment Network to Unify Multimodal Alignment and Unsupervised Domain Adaptation","authors":"Ye Liu, Lingfeng Qiao, Chang-Tien Lu, Di Yin, Chen Lin, Haoyuan Peng, Bo Ren","doi":"10.1109/CVPR52729.2023.00346","DOIUrl":"https://doi.org/10.1109/CVPR52729.2023.00346","url":null,"abstract":"Extending from unimodal to multimodal is a critical challenge for unsupervised domain adaptation (UDA). Two major problems emerge in unsupervised multimodal domain adaptation: domain adaptation and modality alignment. An intuitive way to handle these two problems is to fulfill these tasks in two separate stages: aligning modalities followed by domain adaptation, or vice versa. However, domains and modalities are not associated in most existing two-stage studies, and the relationship between them is not leveraged which can provide complementary information to each other. In this paper, we unify these two stages into one to align domains and modalities simultaneously. In our model, a tensor-based alignment module (TAL) is presented to explore the relationship between domains and modalities. By this means, domains and modalities can interact sufficiently and guide them to utilize complementary information for better results. Furthermore, to establish a bridge between domains, a dynamic domain generator (DDG) module is proposed to build transitional samples by mixing the shared information of two domains in a self-supervised manner, which helps our model learn a domain-invariant common representation space. Extensive experiments prove that our method can achieve superior performance in two real-world applications. The code will be publicly available.","PeriodicalId":376416,"journal":{"name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"32 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":"114783049","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