Learning Invariant Representations has been successfully applied for reconciling a source and a target domain for Unsupervised Domain Adaptation. By investigating the robustness of such methods under the prism of the cluster assumption, we bring new evidence that invariance with a low source risk does not guarantee a well-performing target classifier. More precisely, we show that the cluster assumption is violated in the target domain despite being maintained in the source domain, indicating a lack of robustness of the target classifier. To address this problem, we demonstrate the importance of enforcing the cluster assumption in the target domain, named Target Consistency (TC), especially when paired with Class-Level InVariance (CLIV). Our new approach results in a significant improvement, on both image classification and segmentation benchmarks, over state-of-the-art methods based on invariant representations. Importantly, our method is flexible and easy to implement, making it a complementary technique to existing approaches for improving transferability of representations.
Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo
National Institute of Health Data Science, Peking University(国家健康数据科学研究院,北京大学);School of Artificial Intelligence, Beijing University of Posts and Telecommunications(人工智能学院,北京邮电大学);Wangxuan Institute of Computer Technology at Peking University(北京大学王轩计算机技术研究所);School of Data Science, Fudan University(数据科学学院,复旦大学)
When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey
East China University of Science and Technology(华东理工大学);Oklahoma State University(俄克拉荷马州立大学);Potsdam Institute for Climate Impact Research(波茨坦气候影响研究所);Humboldt University of Berlin(柏林洪堡大学)
Geometric Understanding of Discriminability and Transferability for Visual Domain Adaptation
School of Mathematics, Sun Yat-Sen University(中山大学数学学院);School of Statistics and Mathematics, Guangdong University of Finance and Economics(广东财经大学统计与数学学院);School of Computer Science, Nanjing University of Posts and Telecommunications(南京邮电大学计算机学院)
On the Transferability and Discriminability of Repersentation Learning in Unsupervised Domain Adaptation
National Key Laboratory of Space Integrated Information System, Institute of Software Chinese Academy of Sciences(空间信息集成信息系统国家重点实验室,软件研究所);University of Chinese Academy of Sciences(中国科学院大学);National Key Laboratory of Space Integrated Information System, Department of Computer Science and Technology, Tsinghua University(空间信息集成信息系统国家重点实验室,清华大学计算机科学与技术系);Artificial Intelligence Thrust, Information Hub, Department of Computer Science & Engineering, School of Engineering, Hong Kong University of Science and Technology(人工智能 thrust,信息枢纽,工程学院计算机科学与工程系,香港科学与技术大学)
Zero-shot Domain Adaptation Based on Attribute Information
The University of Tokyo(东京大学);Center for Advanced Intelligence Project, RIKEN(理化学研究所先进智能研究中心);Data Science Research Laboratories, NEC(日本电气公司数据科学研究实验室);Future University Hakodate(函馆未来大学)
Multi-Source Unsupervised Domain Adaptation with Prototype Aggregation
South China University of Technology(华南理工大学);Institute of International Services Outsourcing(国际服务外包研究院);Operation and Maintenance Center of Information and Communication(信息通信运维中心);CSG EHV Power Transmission Company(中国南方电网超高压输电公司)
Multi-Feature Riemannian Hypergraph for Online Test-Time Adaptation of Motor Imagery Brain-Computer Interface
Peking University(北京大学);Chinese Institute for Brain Research(中国脑科学研究院);NeuCyber Neurotech(纽赛博神经科技公司);Beijing Medical University(北京医科大学);Chinese Academy of Medical Sciences & Peking Union Medical College(中国医学科学院北京协和医学院)
School of Software, Tsinghua University, China(清华大学软件学院,中国);Tsinghua University, China(清华大学,中国);University of California, Berkeley, Berkeley, USA(美国加州大学伯克利分校,伯克利)
The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation
School of Artificial Intelligence, Nanjing University(南京大学人工智能学院);National Key Laboratory for Novel Software Technology, Nanjing University(南京大学新型软件技术国家重点实验室);Hong Kong University of Science and Technology(香港科技大学);Frontier Robotics(前沿机器人)
虽然取得了显著的进展,但在没有任何标记数据的情况下,很难诱导出有监督的分类器。无监督的领域自适应能够通过将知识从标记的源域转移到未标记的目标域来克服这一挑战。可转移性和可区分性是表征特征表示的优越性的两个关键标准,以实现成功的领域自适应。在本文中,一种新的方法称为\textit{learning TransFerable and Discriminative Features for unsupervised domain adaptation}(TFDF)提出了这两个目标同时优化。一方面,进行分布对齐以减少域差异并学习更多的可传递表示。在再生核希尔伯特空间(RKHS)中,我们采用了一种新的统计量\textit{Maximum Mean and Covariance Discrepancy}(MMCD),它不仅能捕获一阶统计信息,还能捕获二阶统计信息,而不是采用仅捕获一阶统计信息的\textit{Maximum Mean Discrepancy}(MMD)来度量分布差异.另一方面,我们建议通过流形正则化探索局部判别信息,并通过最小化所提出的\textit{class confusion}目标来学习更多的判别特征,分别探索全局判别信息。我们将这两个目标集成到\textit{Structural Risk Minimization}(RSM)框架中,并学习域不变分类器。在5个真实数据集…
When Unsupervised Domain Adaptation meets One-class Anomaly Detection: Addressing the Two-fold Unsupervised Curse by Leveraging Anomaly Scarcity
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg(安全、可靠性与信任跨学科研究中心(SnT),卢森堡大学);Cristal Laboratory, National School of Computer Sciences, University of Manouba(晶体实验室,国家计算机科学学校,曼努巴大学)
Faculty of Science and Technology, University of Macau(澳门大学科学与技术学院);PolyU Academy for Artificial Intelligence, Hong Kong Polytechnic University(香港理工大学人工智能学院)
Deep into The Domain Shift: Transfer Learning through Dependence Regularization
BNU-HKBU United International College(北京师范大学-香港浸会大学联合国际学院);City University of Hong Kong(香港城市大学);The Laboratory for AI-Powered Financial Technologies Limited(人工智能金融科技实验室有限公司);JD Digits Technology(京东数字科技)
MITA: Bridging the Gap between Model and Data for Test-time Adaptation
Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Pennsylvania State University(宾夕法尼亚州立大学);Kuaishou Technology(快手科技)
Qiushi Academy for Advanced Studies, Zhejiang University(浙江大学求是高等研究院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);Harvard Medical School(哈佛医学院);Cooperative Medianet Innovation Center, Shanghai Jiao Tong University(上海交通大学媒体网络协同创新中心);Shanghai Jiao Tong University(上海交通大学);Shanghai AI Laboratory(上海人工智能实验室);Collaborative Innovation Center for Artificial Intelligence by MOE and Zhejiang Provincial Government (ZJU)(教育部与浙江省政府人工智能协同创新中心(浙江大学));Zhejiang Lab(之江实验室)