Dual-Graph Contrastive Learning for Unsupervised Person Reidentification
- 3 January 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 16 (4) , 1352-1363
Abstract
Unsupervised person re-identification (re-ID) aims to perform person retrieval in an unsupervised manner across multiple cameras. Most recent works usually adopted contrastive learning with clustering strategy to guide learning process. However, the domain gap between cameras easily causes the high intra-class variance and prohibits an effective contrastive learning. To overcome this problem, we propose dual-graph contrastive learning (Dual-GCL) to fully utilize the structures between the instances as well as the relationship between the instances and the centroids generated by the clustering strategy. Firstly, a dual-graph is constructed by utilizing the affinities of instances in the feature space and the pseudo-label space derived from clustering strategy with the node-to-node contrastive learning. Then, to capture the relations between the dual-graph and the centroids, we perform dual-graph contrastive learning at both the node level and the super-node level. The contrastive learning based on the two levels can encode multi-level structural representations between the instances corresponding to the nodes in dual-graph and align the centroids between different cameras in the shared embedding space. Moreover, a camera-aware augmentation scheme that exploits the semantic relationship is proposed to alleviate the domain discrepancy between cameras. Experimental results demonstrate that our approach outperforms the state-of-the-art methods.Keywords
Funding Information
- National Natural Science Foundation of China (61991411, U1913204, 62076148)
- National Key R&D Program of China (2021ZD0112002)
- Natural Science Foundation of Shandong Province for Distinguished Young Scholars (ZR2020JQ29)
- Shandong Excellent Young Scientists Fund Program (2022HWYQ-042)
- Young Taishan Scholars Program of Shandong Province (tsqn201909029)
- Project for Self-Developed Innovation Team of Jinan City (2021GXRC038)
This publication has 53 references indexed in Scilit:
- Cluster Contrast for Unsupervised Person Re-identification2023
- Motion Sensitive Contrastive Learning for Self-supervised Video Representation2022
- PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification2022
- Joint Visual and Temporal Consistency for Unsupervised Domain Adaptive Person Re-identification2020
- CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions2020
- Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification2020
- Multiple Expert Brainstorming for Domain Adaptive Person Re-Identification2020
- Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification2020
- Generalizing a Person Retrieval Model Hetero- and Homogeneously2018
- A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance2016