HARD SAMPLES RECTIFICATION FOR UNSUPERVISED CROSS-DOMAIN PERSON RE-IDENTIFICATION
Journal
Proceedings - International Conference on Image Processing, ICIP
Journal Volume
2021-September
Pages
429-433
Date Issued
2021
Author(s)
Abstract
Person 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 IEEE
Subjects
Computer vision; Person re-identification; Unsupervised learning
Type
conference paper