Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification

• Published in: PloS one Vol. 20; no. 7; p. e0328131
• Main Authors: Bai, Xuemei, Zhang, Yuqing, Zhang, Chenjie, Wang, Zhijun
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 14.07.2025; Public Library of Science (PLoS)
• Subjects: Adaptation; Algorithms; Biology and Life Sciences; Biometric Identification - methods; Cameras; Computer and Information Sciences; Computer vision; Datasets; Effectiveness; Engineering and Technology; Humans; Identification; Identification and classification; Labeling; Labels; Learning; Machine learning; Methods; Optimization; Pedestrians; Physical Sciences; Public safety; Public video surveillance; Research and Analysis Methods; Social Sciences; Surveillance; Technology application; Training; Unsupervised Machine Learning; China

Person re-identification (ReID) technology has many applications in intelligent surveillance and public safety. However, the domain difference between the source and target domains makes the generalization ability of the model extremely challenging. To reduce the dependence on labeled data, Unsuperv...