Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation
South China University of Technology（华南理工大学）；Pengcheng Laboratory（鹏城实验室）；China Tobacco Guangdong Industrial Corporation（广东中烟工业有限责任公司）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Dengke Zhang, Quan Tang, Fagui Liu, Haiqing Mei, C. L. Philip Chen
Semi-supervised semantic segmentation has witnessed remarkable advancements in recent years. However, existing algorithms are based on convolutional neural networks and directly applying them to Vision Transformers poses certain limitations due to conceptual disparities. To this end, we propose TokenMix, a data augmentation technique specifically designed for semi-supervised semantic segmentation with Vision Transformers. TokenMix aligns well with the global attention mechanism by mixing images at the token level, enhancing learning capability for contextual information among image patches. We further incorporate image augmentation and feature augmentation to promote the diversity of augmentation. Moreover, to enhance consistency regularization, we propose a dual-branch framework where each branch applies image and feature augmentation to the input image. We conduct extensive experiments across multiple benchmark datasets, including Pascal VOC 2012, Cityscapes, and COCO. Results suggest that the proposed method outperforms state-of-the-art algorithms with notably observed accuracy improvement, especially under limited fine annotations.
Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation
School of Computer Science and Engineering, Sun Yat-Sen University（中山大学计算机科学与工程学院）；State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所信息安全国家重点实验室）；Beihang University（北京航空航天大学）；University of Chinese Academy of Sciences（中国科学院大学）；School of Cyber Science and Technology, Sun Yat-Sen University（中山大学网络空间科学与技术学院）
Exploring the Robustness of Human Parsers Towards Common Corruptions
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Sun Yat-sen University（中山大学）；Westlake University（西湖大学）；OPPO；Tsinghua University（清华大学）
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
Huazhong University of Science and Technology（华中科技大学）；Microsoft Research Asia（微软亚洲研究院）；Xi’an Jiaotong University（西安交通大学）；University of Science and Technology of China（中国科学技术大学）
SETA: Semantic-Aware Token Augmentation for Domain Generalization
National Institute of Healthcare Data Science, Nanjing University（南京大学国家健康医疗大数据研究院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）
THAT: Token-wise High-frequency Augmentation Transformer for Hyperspectral Pansharpening
JPMorgan Chase（摩根大通公司）；University of Missouri-Kansas City（密苏里大学-堪萨斯城分校）；Ming Hsieh Department of Electrical and Computer Engineering（明希赫电气与计算机工程系）；University of Southern California（南加州大学）；Robinson Research Institute（罗宾逊研究学院）；KTH Royal Institute of Technology（皇家理工学院）；NEC Laboratories America（NEC美国实验室）；University of Virginia（弗吉尼亚大学）
Institute of Biomedical Sciences（生物医学科学研究所）；Universidad de Chile（智利大学）；Universidad de Santiago（圣地亚哥大学）；Institute of Informatics（信息学研究所）；Universidad Austral de Chile（智利奥斯特拉尔大学）
Other Tokens Matter: Exploring Global and Local Features of Vision Transformers for Object Re-Identification
Dalian University of Technology（大连理工大学）；School of Information and Communication Engineering（信息与通信工程学院）；School of Future Technology（未来技术学院）；School of Artificial Intelligence（人工智能学院）
ZACH-ViT: A Zero-Token Vision Transformer with ShuffleStrides Data Augmentation for Robust Lung Ultrasound Classification
Amsterdam UMC, University of Amsterdam, The Netherlands（阿姆斯特丹大学医学中心，阿姆斯特丹大学，荷兰）；Data Science Center, University of Amsterdam, The Netherlands（数据科学中心，阿姆斯特丹大学，荷兰）；Department of Intensive Care Medicine, Amsterdam UMC, University of Amsterdam & Vrije Universiteit Amsterdam, The Netherlands（重症医学科，阿姆斯特丹大学医学中心，阿姆斯特丹大学及自由大学，荷兰）
Exploring Structure Consistency for Deep Model Watermarking
University of Science and Technology of China（中国科学技术大学）；Microsoft Cloud AI（微软云人工智能部门）；City University of Hong Kong（香港城市大学）；Wormpex AI Research（Wormpex人工智能研究院）
Exploring the Design Space of Visual Context Representation in Video MLLMs
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Baichuan Inc.（百川公司）；School of Information, Renmin University of China（中国人民大学信息学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
