Learning Domain Adaptive Object Detection with Probabilistic Teacher
Zhejiang University（浙江大学）；Hikvision Research Institute（海康威视研究院）；National University of Singapore（新加坡国立大学）；Chongqing University（重庆大学）；Hainan Institute of Zhejiang University（浙江大学海南研究院）
Meilin Chen, Weijie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Yunfeng Yan, Donglian Qi, Yueting Zhuang, Di Xie, Shiliang Pu
Self-training for unsupervised domain adaptive object detection is a challenging task, of which the performance depends heavily on the quality of pseudo boxes. Despite the promising results, prior works have largely overlooked the uncertainty of pseudo boxes during self-training. In this paper, we present a simple yet effective framework, termed as Probabilistic Teacher (PT), which aims to capture the uncertainty of unlabeled target data from a gradually evolving teacher and guides the learning of a student in a mutually beneficial manner. Specifically, we propose to leverage the uncertainty-guided consistency training to promote classification adaptation and localization adaptation, rather than filtering pseudo boxes via an elaborate confidence threshold. In addition, we conduct anchor adaptation in parallel with localization adaptation, since anchor can be regarded as a learnable parameter. Together with this framework, we also present a novel Entropy Focal Loss (EFL) to further facilitate the uncertainty-guided self-training. Equipped with EFL, PT outperforms all previous baselines by a large margin and achieve new state-of-the-arts.
Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
Beihang University（北京航空航天大学）；Shenzhen Institutes of Advanced Technology, Chinese Academy of Science（中国科学院深圳先进技术研究院）；SenseTime Research（商汤科技研究院）；Shanghai AI Laboratory（上海人工智能实验室）
CLDA-YOLO: Visual Contrastive Learning Based Domain Adaptive YOLO Detector
University of Science and Technology of China（中国科学技术大学）；Hefei Institutes of Physical Science, Chinese Academy of Sciences（中国科学院合肥物质科学研究院）；SenseTime Research（商汤科技研究院）；Tsinghua University（清华大学）
Adaptive Knowledge Transferring with Switching Dual-Student Framework for Semi-Supervised Medical Image Segmentation
North Carolina A&T State University（北卡罗来纳农工州立大学）；Carnegie Mellon University（卡内基梅隆大学）；Ho Chi Minh University of Technology（胡志明市理工大学）；University of Pittsburgh（匹兹堡大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）
Customizing Student Networks From Heterogeneous Teachers via Adaptive Knowledge Amalgamation
Zhejiang University（浙江大学）；Stevens Institute of Technology（史蒂文斯理工学院）；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）
DAIT: Distillation from Vision-Language Models to Lightweight Classifiers with Adaptive Intermediate Teacher Transfer
School of Computer and Electronic Information, Nanjing Normal University, Nanjing, China（南京师范大学计算机与电子信息学院）；Medical Artificial Intelligence Lab, Westlake University（西湖大学医学人工智能实验室）
Improving Adversarial Robustness Through Adaptive Learning-Driven Multi-Teacher Knowledge Distillation
Intelligent Systems, Computer Architecture, Analytics, and Security Laboratory (ISCAAS Lab), Department of Electrical Engineering and Computer Science, Florida Atlantic University（智能系统、计算机架构、分析与安全实验室（ISCAAS实验室），电气工程与计算机科学系，佛罗里达 Atlantic 大学）；Intelligent Systems, Computer Architecture, Analytics, and Security Laboratory (ISCAAS Lab), Department of Computer Science, Kansas State University（智能系统、计算机架构、分析与安全实验室（ISCAAS实验室），计算机科学系，堪萨斯州立大学）
Graduate School of Advanced Science and Engineering Hiroshima University（广岛大学先进科学与工程学院）；Intelligent Production Technology Research & Development Center for Aerospace Gifu University（岐阜大学航空航天智能生产技术研究开发中心）
Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation
Center for Frontier AI Research, Agency for Science, Technology, and Research（新加坡科技研究局前沿人工智能研究中心）；Huazhong University of Science and Technology（华中科技大学）；Zhejiang University（浙江大学）；Dalian University of Technology（大连理工大学）
Knowledge distillation via adaptive instance normalization
Computer Vision Laboratory, University of Nottingham, UK（诺丁汉大学计算机视觉实验室）；Samsung AI Center, Cambridge, UK（三星人工智能中心剑桥）；Queen Mary University of London, London, UK（伦敦玛丽女王大学）
SloMo-Fast: Slow-Momentum and Fast-Adaptive Teachers for Source-Free Continual Test-Time Adaptation
Center for Computational & Data Sciences, Independent University, Bangladesh（计算与数据科学中心，独立大学，孟加拉国）；University of Central Florida, USA（佛罗里达中央大学，美国）；University of Virginia, USA（弗吉尼亚大学，美国）；Amazon GenAI, USA（亚马逊生成人工智能，美国）
Feature-domain Adaptive Contrastive Distillation for Efficient Single Image Super-Resolution
Korea Electronics Technology Institutes（韩国电子技术研究院）
最近，基于CNN的SISR具有许多参数和高计算成本以实现更好的性能，限制了其对资源受限设备（如移动设备）的适用性。知识蒸馏（KD）是使网络高效的方法之一，它将教师的有用知识传递给学生，目前正在研究中。最近，KD for SISR利用特征蒸馏（FD）来最小化教师和学生网络之间特征图的欧氏距离损失，但它没有充分考虑如何有效地和有意义地从教师那里传递知识，以提高学生在给定网络容量限制下的表现。在本文中，我们提出了一个特征域自适应对比蒸馏（FACD）方法，有效地训练轻量级学生SISR网络。我们使用欧氏距离损失现有FD方法的局限性，并提出了一个特征域对比损失，使学生网络学习更丰富的信息，从教师的代表在特征域。此外，我们提出了一种自适应蒸馏，根据训练补丁的条件选择性地应用蒸馏。实验结果表明，学生EDSR和RCAN网络与建议的FACD计划不仅提高了整个基准数据集和规模的PSNR性能，而且与传统的FD方法相比，主观图像质量。
Adaptive Dual-Teacher Distillation with Subnetwork Rectification for Bridging Semantic Gaps in Black-Box Domain Adaptation
School of Computer Science and Engineering, Tianjin University of Technology（天津理工大学计算机科学与工程学院）；School of Artificial Intelligence, Tianjin University（天津大学人工智能学院）
