Journal
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
Volume 18, Issue 2, Pages -Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3485061
Keywords
Person re-identification; unsupervised learning; contrastive learning
Categories
Funding
- National Key Research and Development Project [2019YFE0109600]
- National Science Foundation of China [61922027, 61971165, 61932022]
Ask authors/readers for more resources
This study proposes a novel selective contrastive learning framework for fully unsupervised feature learning. Experimental results demonstrate the superiority of the method in unsupervised person ReID compared with the state of the art.
Person re-identification (ReID) aims at searching the same identity person among images captured by various cameras. Existing fully supervised person ReID methods usually suffer from poor generalization capability caused by domain gaps. Unsupervised person ReID has attracted a lot of attention recently, because it works without intensive manual annotation and thus shows great potential in adapting to new conditions. Representation learning plays a critical role in unsupervised person ReID. In this work, we propose a novel selective contrastive learning framework for fully unsupervised feature learning. Specifically, different from traditional contrastive learning strategies, we propose to use multiple positives and adaptively selected negatives for defining the contrastive loss, enabling to learn a feature embedding model with stronger identity discriminative representation. Moreover, we propose to jointly leverage global and local features to construct three dynamic memory banks, among which the global and local ones are used for pairwise similarity computation and the mixture memory bank are used for contrastive loss definition. Experimental results demonstrate the superiority of our method in unsupervised person ReID compared with the state of the art. Our code is available at https://github.com/pangbo1997/Unsup ReID.git.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available