Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification

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...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2022, Vol.31, p.1-1
Main Authors: Wu, Lin, Liu, Deyin, Zhang, Wenying, Chen, Dapeng, Ge, Zongyuan, Boussaid, Farid, Bennamoun, Mohammed, Shen, Jialie
Format: Article
Language:English
Subjects:
Annotations
Australia
Cameras
Clustering
Convolution
Electronic mail
Formability
Labels
Learning
Person re-identification
Pseudo pair construction
Self-similarity
Self-similarity learning
Surveillance systems
Training
Unsupervised learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2022.3186746