In this work, we propose a novel complementary learning approach to enhance test-time adaptation (TTA), which has been proven to exhibit good performance on testing data with distribution shifts such as corruptions. In test-time adaptation tasks, information from the source domain is typically unavailable and the model has to be optimized without supervision for test-time samples. Hence, usual methods assign labels for unannotated data with the prediction by a well-trained source model in an unsupervised learning framework. Previous studies have employed unsupervised objectives, such as the entropy of model predictions, as optimization targets to effectively learn features for test-time samples. However, the performance of the model is easily compromised by the quality of pseudo-labels, since inaccuracies in pseudo-labels introduce noise to the model. Therefore, we propose to leverage the "less probable categories" to decrease the risk of incorrect pseudo-labeling. The complementary label is introduced to designate these categories. We highlight that the risk function of complementary labels agrees with their Vanilla loss formula under the conventional true label distribution. Experiments show that the proposed learning algorithm achieves state-of-the-art performance on different datasets and experiment settings.
The University of Sydney（悉尼大学）；SenseTime Computer Vision Research Group（商汤科技计算机视觉研究组）；SenseTime Research（商汤科技研究院）；Dalian University of Technology（大连理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Rethinking Pseudo-Label Guided Learning for Weakly Supervised Temporal Action Localization from the Perspective of Noise Correction
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院）
Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You Need
Digital Medical Research Center, School of Basic Medical Science, Fudan University（复旦大学基础医学院数字医学研究中心）；Fudan University Shanghai Cancer Center（复旦大学附属肿瘤医院）
Rethinking Multiple Instance Learning: Developing an Instance-Level Classifier via Weakly-Supervised Self-Training
Digital Medical Research Center, School of Basic Medical Science, Fudan University（复旦大学基础医学院数字医学研究中心）；Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention（上海市医学影像计算与计算机辅助介入重点实验室）
Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replay
The Chinese University of Hong Kong（香港中文大学）；Northeastern University（东北大学）；The University of Sydney（悉尼大学）；National University of Singapore（新加坡国立大学）；Suzhou Research Institute, National University of Singapore（新加坡国立大学苏州研究院）；Shun Hing Institute of Advanced Engineering, The Chinese University of Hong Kong（香港中文大学信兴高等工程研究院）；Shenzhen Research Institute, The Chinese University of Hong Kong（香港中文大学深圳研究院）
Complementary Pseudo Labels For Unsupervised Domain Adaptation On Person Re-identification
Zhejiang University（浙江大学）；Alibaba-Zhejiang University Joint Institute of Frontier Technologies（阿里巴巴-浙江大学前沿技术联合研究院）；College of Computer Science, Zhejiang University（浙江大学计算机学院）
IP-SAM: Rethinking Prompt-Conditioned Segmentation for Prompt-Absent Deployment
University of Chinese Academy of Sciences（中国科学院大学）；Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences（中国科学院空间应用工程与技术中心）
Rethinking Barely-Supervised Volumetric Medical Image Segmentation from an Unsupervised Domain Adaptation Perspective
School of Computer Science and Engineering, Northeastern University（东北大学计算机科学与工程学院）；Alberta Machine Intelligence Institute, University of Alberta（阿尔伯塔大学阿尔伯塔机器智能研究所）
Rethinking Sampling Strategies for Unsupervised Person Re-identification
University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Institute of North Electronic Equipment（北方电子设备研究所）；Peng Cheng Laboratory（鹏城实验室）；Tianjin University（天津大学）
本文研究无监督行人重识别中的采样策略，提出 group sampling 分组采样以缓解过拟合并增强统计稳定性，在三个基准上取得与最先进方法相当或更优的性能。
Rethinking Dense Optical Flow without Test-Time Scaling
Visual and Spatial AI Lab（视觉与空间人工智能实验室）；VCCM Section College of PVFA（VCCM学院光电工程学院）；Department of ECEN（电子工程系）；Department of CSCE（计算机科学与工程系）；Texas A&M University（德克萨斯A&M大学）
Rethinking the Role of Pre-Trained Networks in Source-Free Domain Adaptation
Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局（A*STAR）前沿人工智能研究中心（CFAR））；Institute for Infocomm Research (IR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局（A*STAR）资讯通信研究院（IR））
Rethinking the Adaptation of Vision Foundation Models for Efficient Cell Segmentation
School of Computer Science, University of Nottingham, UK（英国诺丁汉大学计算机科学学院）；School of Computer Science, University of Nottingham Ningbo China, China（中国宁波诺丁汉大学计算机科学学院）；School of Engineering and Physical Science, University of Lincoln, UK（英国林肯大学工程与物理科学学院）；Department of Computer Science, University of Rochester, USA（美国罗切斯特大学计算机科学系）
PMMTalk: Speech-Driven 3D Facial Animation from Complementary Pseudo Multi-modal Features
Macau University of Science and Technology（澳门科技大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology Beijing（北京科技大学）；Mashang Consumer Finance Co., Ltd（马上消费金融股份有限公司）
