2021 IEEE/CVF International Conference on Computer Vision (ICCV)最新文献_第8页

Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment 基于统一特征学习和优化目标对齐的非iid数据联邦学习

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.00438

Lin Zhang, Yongliang Luo, Yan Bai, Bo Du, Ling-yu Duan

{"title":"Federated Learning for Non-IID Data via Unified Feature Learning and Optimization Objective Alignment","authors":"Lin Zhang, Yongliang Luo, Yan Bai, Bo Du, Ling-yu Duan","doi":"10.1109/ICCV48922.2021.00438","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00438","url":null,"abstract":"Federated Learning (FL) aims to establish a shared model across decentralized clients under the privacy-preserving constraint. Despite certain success, it is still challenging for FL to deal with non-IID (non-independent and identical distribution) client data, which is a general scenario in real-world FL tasks. It has been demonstrated that the performance of FL will be reduced greatly under the non-IID scenario, since the discrepant data distributions will induce optimization inconsistency and feature divergence issues. Besides, naively minimizing an aggregate loss function in this scenario may have negative impacts on some clients and thus deteriorate their personal model performance. To address these issues, we propose a Unified Feature learning and Optimization objectives alignment method (FedUFO) for non-IID FL. In particular, an adversary module is proposed to reduce the divergence on feature representation among different clients, and two consensus losses are proposed to reduce the inconsistency on optimization objectives from two perspectives. Extensive experiments demonstrate that our FedUFO can outperform the state-of-the-art approaches, including the competitive one data-sharing method. Besides, FedUFO can enable more reasonable and balanced model performance among different clients.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"60 1","pages":"4400-4408"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88755926","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: 34

Domain-Invariant Disentangled Network for Generalizable Object Detection 泛化目标检测的域不变解纠缠网络

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.00865

Chuang Lin, Zehuan Yuan, Sicheng Zhao, Pei Sun, Changhu Wang, Jianfei Cai

{"title":"Domain-Invariant Disentangled Network for Generalizable Object Detection","authors":"Chuang Lin, Zehuan Yuan, Sicheng Zhao, Pei Sun, Changhu Wang, Jianfei Cai","doi":"10.1109/ICCV48922.2021.00865","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00865","url":null,"abstract":"We address the problem of domain generalizable object detection, which aims to learn a domain-invariant detector from multiple \"seen\" domains so that it can generalize well to other \"unseen\" domains. The generalization ability is crucial in practical scenarios especially when it is difficult to collect data. Compared to image classification, domain generalization in object detection has seldom been explored with more challenges brought by domain gaps on both image and instance levels. In this paper, we propose a novel generalizable object detection model, termed Domain-Invariant Disentangled Network (DIDN). In contrast to directly aligning multiple sources, we integrate a disentangled network into Faster R-CNN. By disentangling representations on both image and instance levels, DIDN is able to learn domain-invariant representations that are suitable for generalized object detection. Furthermore, we design a cross-level representation reconstruction to complement this two-level disentanglement so that informative object representations could be preserved. Extensive experiments are conducted on five benchmark datasets and the results demonstrate that our model achieves state-of-the-art performances on domain generalization for object detection.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"1 1","pages":"8751-8760"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77350547","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: 42

RFNet: Region-aware Fusion Network for Incomplete Multi-modal Brain Tumor Segmentation 基于区域感知的脑肿瘤不完全多模态分割融合网络

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.00394

Yuhang Ding, Xin Yu, Yi Yang

{"title":"RFNet: Region-aware Fusion Network for Incomplete Multi-modal Brain Tumor Segmentation","authors":"Yuhang Ding, Xin Yu, Yi Yang","doi":"10.1109/ICCV48922.2021.00394","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00394","url":null,"abstract":"Most existing brain tumor segmentation methods usually exploit multi-modal magnetic resonance imaging (MRI) images to achieve high segmentation performance. However, the problem of missing certain modality images often happens in clinical practice, thus leading to severe segmentation performance degradation. In this work, we propose a Region-aware Fusion Network (RFNet) that is able to exploit different combinations of multi-modal data adaptively and effectively for tumor segmentation. Considering different modalities are sensitive to different brain tumor regions, we design a Region-aware Fusion Module (RFM) in RFNet to conduct modal feature fusion from available image modalities according to disparate regions. Benefiting from RFM, RFNet can adaptively segment tumor regions from an incomplete set of multi-modal images by effectively aggregating modal features. Furthermore, we also develop a segmentation-based regularizer to prevent RFNet from the insufficient and unbalanced training caused by the incomplete multi-modal data. Specifically, apart from obtaining segmentation results from fused modal features, we also segment each image modality individually from the corresponding encoded features. In this manner, each modal encoder is forced to learn discriminative features, thus improving the representation ability of the fused features. Remarkably, extensive experiments on BRATS2020, BRATS2018 and BRATS2015 datasets demonstrate that our RFNet outperforms the state-of-the-art significantly.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"27 1","pages":"3955-3964"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77374110","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: 22

Self-Mutual Distillation Learning for Continuous Sign Language Recognition 连续手语识别的自互蒸馏学习

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.01111

Aiming Hao, Yuecong Min, Xilin Chen

{"title":"Self-Mutual Distillation Learning for Continuous Sign Language Recognition","authors":"Aiming Hao, Yuecong Min, Xilin Chen","doi":"10.1109/ICCV48922.2021.01111","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.01111","url":null,"abstract":"In recent years, deep learning moves video-based Continuous Sign Language Recognition (CSLR) significantly forward. Currently, a typical network combination for CSLR includes a visual module, which focuses on spatial and short-temporal information, followed by a contextual module, which focuses on long-temporal information, and the Connectionist Temporal Classification (CTC) loss is adopted to train the network. However, due to the limitation of chain rules in back-propagation, the visual module is hard to adjust for seeking optimized visual features. As a result, it enforces that the contextual module focuses on contextual information optimization only rather than balancing efficient visual and contextual information. In this paper, we propose a Self-Mutual Knowledge Distillation (SMKD) method, which enforces the visual and contextual modules to focus on short-term and long-term information and enhances the discriminative power of both modules simultaneously. Specifically, the visual and contextual modules share the weights of their corresponding classifiers, and train with CTC loss simultaneously. Moreover, the spike phenomenon widely exists with CTC loss. Although it can help us choose a few of the key frames of a gloss, it does drop other frames in a gloss and makes the visual feature saturation in the early stage. A gloss segmentation is developed to relieve the spike phenomenon and decrease saturation in the visual module. We conduct experiments on two CSLR bench-marks: PHOENIX14 and PHOENIX14-T. Experimental results demonstrate the effectiveness of the SMKD.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"946 1","pages":"11283-11292"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77571849","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: 45

A Simple Feature Augmentation for Domain Generalization 一种用于领域泛化的简单特征增强

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.00876

Pan Li, Da Li, Wei Li, S. Gong, Yanwei Fu, Timothy M. Hospedales

{"title":"A Simple Feature Augmentation for Domain Generalization","authors":"Pan Li, Da Li, Wei Li, S. Gong, Yanwei Fu, Timothy M. Hospedales","doi":"10.1109/ICCV48922.2021.00876","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00876","url":null,"abstract":"The topical domain generalization (DG) problem asks trained models to perform well on an unseen target domain with different data statistics from the source training domains. In computer vision, data augmentation has proven one of the most effective ways of better exploiting the source data to improve domain generalization. However, existing approaches primarily rely on image-space data augmentation, which requires careful augmentation design, and provides limited diversity of augmented data. We argue that feature augmentation is a more promising direction for DG. We find that an extremely simple technique of perturbing the feature embedding with Gaussian noise during training leads to a classifier with domain-generalization performance comparable to existing state of the art. To model more meaningful statistics reflective of cross-domain variability, we further estimate the full class-conditional feature covariance matrix iteratively during training. Subsequent joint stochastic feature augmentation provides an effective domain randomization method, perturbing features in the directions of intra-class/cross-domain variability. We verify our proposed method on three standard domain generalization benchmarks, Digit-DG, VLCS and PACS, and show it is outperforming or comparable to the state of the art in all setups, together with experimental analysis to illustrate how our method works towards training a robust generalisable model.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"os-27 1","pages":"8866-8875"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87208790","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: 95

Not All Operations Contribute Equally: Hierarchical Operation-adaptive Predictor for Neural Architecture Search 并非所有操作贡献相同:神经结构搜索的分层操作自适应预测器

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.01034

Ziye Chen, Yibing Zhan, Baosheng Yu, Mingming Gong, Bo Du

引用次数: 6

Temporal Cue Guided Video Highlight Detection with Low-Rank Audio-Visual Fusion 基于低秩视听融合的时间线索引导视频高光检测

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.00785

Qinghao Ye, Xi Shen, Yuan Gao, Zirui Wang, Qi Bi, Ping Li, Guang Yang

{"title":"Temporal Cue Guided Video Highlight Detection with Low-Rank Audio-Visual Fusion","authors":"Qinghao Ye, Xi Shen, Yuan Gao, Zirui Wang, Qi Bi, Ping Li, Guang Yang","doi":"10.1109/ICCV48922.2021.00785","DOIUrl":"https://doi.org/10.1109/ICCV48922.2021.00785","url":null,"abstract":"Video highlight detection plays an increasingly important role in social media content filtering, however, it remains highly challenging to develop automated video highlight detection methods because of the lack of temporal annotations (i.e., where the highlight moments are in long videos) for supervised learning. In this paper, we propose a novel weakly supervised method that can learn to detect highlights by mining video characteristics with video level annotations (topic tags) only. Particularly, we exploit audio-visual features to enhance video representation and take temporal cues into account for improving detection performance. Our contributions are threefold: 1) we propose an audio-visual tensor fusion mechanism that efficiently models the complex association between two modalities while reducing the gap of the heterogeneity between the two modalities; 2) we introduce a novel hierarchical temporal context encoder to embed local temporal clues in between neighboring segments; 3) finally, we alleviate the gradient vanishing problem theoretically during model optimization with attention-gated instance aggregation. Extensive experiments on two benchmark datasets (YouTube Highlights and TVSum) have demonstrated our method outperforms other state-of-the-art methods with remarkable improvements.","PeriodicalId":6820,"journal":{"name":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"2013 1","pages":"7930-7939"},"PeriodicalIF":0.0,"publicationDate":"2021-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87736088","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: 17

Parallel Multi-Resolution Fusion Network for Image Inpainting 并行多分辨率融合网络用于图像绘制

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.01429

Wentao Wang, Jianfu Zhang, Li Niu, Haoyu Ling, Xue Yang, Liqing Zhang

引用次数: 20

Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans Omnidata:用于从3D扫描制作多任务中级视觉数据集的可扩展管道

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.01061

Ainaz Eftekhar, Alexander Sax, Roman Bachmann, J. Malik, A. Zamir

引用次数: 97

Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents 异质协同具身代理中突发通信的解释

2021 IEEE/CVF International Conference on Computer Vision (ICCV) Pub Date : 2021-10-01 DOI: 10.1109/ICCV48922.2021.01565

Shivansh Patel, Saim Wani, Unnat Jain, A. Schwing, S. Lazebnik, M. Savva, Angel X. Chang

引用次数: 18