Joint Generative and Contrastive Learning for Unsupervised Person Re-identification - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Joint Generative and Contrastive Learning for Unsupervised Person Re-identification

Résumé

Recent self-supervised contrastive learning provides an effective approach for unsupervised person re-identification (ReID) by learning invariance from different views (transformed versions) of an input. In this paper, we incorporate a Generative Adversarial Network (GAN) and a contrastive learning module into one joint training framework. While the GAN provides online data augmentation for contrastive learning, the contrastive module learns view-invariant features for generation. In this context, we propose a meshbased view generator. Specifically, mesh projections serve as references towards generating novel views of a person. In addition, we propose a view-invariant loss to facilitate contrastive learning between original and generated views. Deviating from previous GAN-based unsupervised ReID methods involving domain adaptation, we do not rely on a labeled source dataset, which makes our method more flexible. Extensive experimental results show that our method significantly outperforms state-of-the-art methods under both, fully unsupervised and unsupervised domain adaptive settings on several large scale ReID datsets. Source code and models are available under https: //github.com/chenhao2345/GCL.
Fichier principal
Vignette du fichier
cvpr2021_Joint_Generative_and_Contrastive_Learning_for_Unsupervised_Person_Re_identification (2).pdf (2.77 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03349257 , version 1 (20-09-2021)

Identifiants

  • HAL Id : hal-03349257 , version 1

Citer

Hao Chen, Yaohui Wang, Benoit Lagadec, Antitza Dantcheva, Francois F Bremond. Joint Generative and Contrastive Learning for Unsupervised Person Re-identification. CVPR 2021 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2021, Virtual, United States. ⟨hal-03349257⟩
49 Consultations
48 Téléchargements

Partager

Gmail Facebook X LinkedIn More