文献类型：期刊文献

英文题名：UC-SFDA: Source-free domain adaptation via uncertainty prediction and evidence-based contrastive learning

作者：Chen, Dong[1];Zhu, Hongqing[1];Yang, Suyi[2]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Kings Coll London, Dept Math Nat Math & Engn Sci, London WC2R 2LS, England

年份：2023

卷号：275

外文期刊名：KNOWLEDGE-BASED SYSTEMS

收录：;EI(收录号：20232714330499);WOS:【SCI-EXPANDED(收录号:WOS:001036660900001)】；

基金：The authors would like to thank the anonymous reviewers and the associate editor for their insightful comments that sig-nificantly improved the quality of this paper. This work was supported by the National Natural Science Foundation of China under Grant 61872143.

语种：英文

外文关键词：Evidence theory; Contrastive learning; Source-free domain adaptation; Uncertainty prediction; High-confidence

摘要：Most unsupervised domain adaptation approaches learn domain-invariant features assuming that source and target domain data are available simultaneously. In practice, the availability of source samples is only sometimes possible. This paper establishes a novel source-free domain adaptation (SFDA) framework based on uncertainty prediction and a neighborhood-guided evidence-based contrastive learning scheme. First, we develop an evidence analyzer based on the uncertainty prediction principle of Dempster-Shafer (D-S) evidence theory, which improves the network capability for discriminating different types of samples. The transformer layer with a self-attention module is adopted to capture long-distance feature dependencies such that the proposed network has better generalization ability on multiple domains. Then, we offer a high-confidence target domain sample (HCS) acquisition strategy through evidence theory, entropy criterion, and distance information. A joint confidence enhancement scheme obtains the final HCS that generates pseudo-labels. Finally, we propose an optimization method based on evidence theory, evidence-based comparative learning, and internal neighborhood structure to ensure the separability between classes and compactness within categories. Experimental results show that the proposed framework performs superiorly on two standard datasets on multiple adaptation tasks. The code for this project is available at github.com/oolown/UC-SFDA.& COPY; 2023 Elsevier B.V. All rights reserved.