Liu C.-TLee M.-YChen T.-SSHAO-YI CHIEN2023-06-092023-06-09202115224880https://www.scopus.com/inward/record.uri?eid=2-s2.0-85125568761&doi=10.1109%2fICIP42928.2021.9506099&partnerID=40&md5=452d24f80027970b7bd9d4a3a3b1222dhttps://scholars.lib.ntu.edu.tw/handle/123456789/632363Person re-identification (re-ID) has received great success with the supervised learning methods. However, the task of unsupervised cross-domain re-ID is still challenging. In this paper, we propose a Hard Samples Rectification (HSR) learning scheme which resolves the weakness of original clustering-based methods being vulnerable to the hard positive and negative samples in the target unlabelled dataset. Our HSR contains two parts, an inter-camera mining method that helps recognize a person under different views (hard positive) and a part-based homogeneity technique that makes the model discriminate different persons but with similar appearance (hard negative). By rectifying those two hard cases, the re-ID model can learn effectively and achieve promising results on two large-scale benchmarks. © 2021 IEEEComputer vision; Person re-identification; Unsupervised learning[SDGs]SDG10[SDGs]SDG11conference paper10.1109/ICIP42928.2021.95060992-s2.0-85125568761