Paper Info
Title
Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
Abstract
Visible-infrared person re-identification (VI-ReID) is a challenging and essential task in night-time intelligent surveillance systems. Except for the intra-modality variance that RGB-RGB person re-identification mainly overcomes, VI-ReID suffers from additional inter-modality variance caused by the inherent heterogeneous gap. To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively. Disentangling cross-modality identity-discriminable features leads to more robust retrieval for VI-ReID. To achieve efficient optimization like conventional VAE, we theoretically derive two variational inference terms for the MoG prior under the supervised setting, which not only restricts the identity-discriminable subspace so that the model explicitly handles the cross-modality intra-identity variance, but also enables the MoG distribution to avoid posterior collapse. Furthermore, we propose a triplet swap reconstruction (TSR) strategy to promote the above disentangling process. Extensive experiments demonstrate that our method outperforms state-of-the-art methods on two VI-ReID datasets. Codes will be available at https://github.com/TPCD/DG-VAE.
Year
DOI
Venue
2020
10.1145/3394171.3413673
MM '20: The 28th ACM International Conference on Multimedia Seattle WA USA October, 2020
DocType
ISBN
Citations 
Conference
978-1-4503-7988-5
3
PageRank 
References 
Authors
0.37
15
5
Name
Order
Citations
PageRank
Nan Pu133.41
Wei Chen21711246.70
Yu Liu319825.45
Erwin M. Bakker437841.20
Michael S. Lew52742166.02