City Research Online

Pseudo-Pair Based Self-Similarity Learning for Unsupervised Person Re-Identification

Wu, L., Liu, D., Zhang, W. , Chen, D., Ge, Z., Boussaid, F., Bennamoun, M. & Shen, J. ORCID: 0000-0001-6895-7413 (2022). Pseudo-Pair Based Self-Similarity Learning for Unsupervised Person Re-Identification. IEEE Transactions on Image Processing, 31, pp. 4803-4816. doi: 10.1109/TIP.2022.3186746


Person re-identification (re-ID) is of great importance to video surveillance systems by estimating the similarity between a pair of cross-camera person shorts. Current methods for estimating such similarity require a large number of labeled samples for supervised training. In this paper, we present a pseudo-pair based self-similarity learning approach for unsupervised person re-ID without human annotations. Unlike conventional unsupervised re-ID methods that use pseudo labels based on global clustering, we construct patch surrogate classes as initial supervision, and propose to assign pseudo labels to images through the pairwise gradient-guided similarity separation. This can cluster images in pseudo pairs, and the pseudos can be updated during training. Based on pseudo pairs, we propose to improve the generalization of similarity function via a novel self-similarity learning:it learns local discriminative features from individual images via intra-similarity, and discovers the patch correspondence across images via inter-similarity. The intra-similarity learning is based on channel attention to detect diverse local features from an image. The inter-similarity learning employs a deformable convolution with a non-local block to align patches for cross-image similarity. Experimental results on several re-ID benchmark datasets demonstrate the superiority of the proposed method over the state-of-the-arts.

Publication Type: Article
Additional Information: © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Publisher Keywords: Training, Electronic mail, Unsupervised learning, Australia, Annotations, Convolution, Cameras
Departments: School of Science & Technology > Computer Science
Text - Accepted Version
Download (6MB) | Preview



Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login