Research Area:  Machine Learning

Abstract:

In this paper, we propose a novel unsupervised domain adaptation re-ID framework by fusing feature adversarial learning and self-similarity clustering. Different from most of the existing works which only regard the source domain data as network pretraining data, we use the source domain data both in network pretraining and finetuing stage. Concretely, we construct an feature adversarial learning module to learn domain invariant feature representations. The feature extractor network is optimized in an adversarial training manner through minimizing the discrepancy of feature representations between source and target domains. To further enhance the discriminability of the feature extractor network, we design the self-similarity clustering module to mine the implicit similarity relationships among the unlabeled samples of the target domain. By unsupervised clustering, we can generate pseudo-identity labels for the target domain data, which are then combined with the labeled source data together to train the feature extractor network. Additionally, we present a relabeling algorithm to construct correspondence between two groups of pseudo-identity labels generated by two iterative clusterings. Experimental results validate the effectiveness of our method.

Keywords:  
Unsupervised domain
adaptive re-identification
Feature adversarial learning
Self-similarity clustering

Author(s) Name:  Tianyi Yan, Haiyun Guo,Songyan Liu, Chaoyang Zhao, Ming Tang & Jinqiao Wang

Publisher name:  Springer

DOI:  10.1007/978-3-030-68799-1_2

Volume Information:  

Paper Link:   https://link.springer.com/chapter/10.1007/978-3-030-68799-1_2