Distance constraint between features for unsupervised domain adaptive person re-identification

Abstract Many superior person re-identification (re-ID) approaches face a challenge: their performance show disastrous when all supervised models are generalized to a new domain. Some researchers have recently proposed domain adaptive person re-ID methods to address this difficulty, whereas they directly leveraged the target-domain data that would generate lots of noisy pseudo labels. Hence, this paper proposes a distance constraint between features (DCF) method, which clusters the feature distribution fitted the real target-domain data. We assemble different parts of one person for multi-scale self-supervised learning. After introducing domain invariance and designing the inter-image and inter-class distance constraint to regulate distances between target samples, the feature distribution extracted from the encoder trained by the source data can fit the real target data distribution, which leads our domain adaptive model to enjoy the more reliable clustering results and thus obtain a great identification performance in target domain. Extensive experiments demonstrate our approach outperforms state-of-the-art methods on three large-scale released datasets.