Unsupervised cross-domain person re-identification by instance and distribution alignment. (April 2022)

• Record Type: Journal Article
• Authors: Lan, Xu; Zhu, Xiatian; Gong, Shaogang
• Is Part Of: Pattern recognition. Volume 124(2022)
• Publication Date: 2022-04
• Subjects: Unsupervise person re-identification -- Domain adaptation; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108514
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: A novel idea of exploring instance-wise localised source knowledge for unsupervised cross-domain person re-id. A Hierarchical Unsupervised Domain Adaptation method designed to discover localised source knowledge at the instance level. A Analyse feature representations for domain adaptation in closed-set supervised learning vs. open-set unsupervised learning. Abstract: Most existing person re-identification (re-id) methods assume supervised model training on a separate large set of training samples from the target domain. While performing well in the training domain, such trained models are seldom generalisable to a new independent unsupervised target domain without further labelled training data from the target domain. To solve this scalability limitation, we develop a novel Hierarchical Unsupervised Domain Adaptation (HUDA) method. It can transfer labelled information of an existing dataset (a source domain) to an unlabelled target domain for unsupervised person re-id. Specifically, HUDA is designed to model jointly global distribution alignment and local instance alignment in a two-level hierarchy for discovering transferable source knowledge in unsupervised domain adaptation. Crucially, this approach aims to overcome the under-constrained learning problem of existing unsupervised domain adaptation methods. Extensive evaluations show the superiority of HUDA for unsupervised cross-domain person re-id over a wide variety of state-of-the-art methods on four re-id benchmarks: Market-1501, DukeMTMC, MSMT17 and CUHK03.