Learning Invariance from Generated Variance for Unsupervised Person Re-identification - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2022

Learning Invariance from Generated Variance for Unsupervised Person Re-identification

Résumé

This work focuses on unsupervised representation learning in person re-identification (ReID). Recent self-supervised contrastive learning methods learn invariance by maximizing the representation similarity between two augmented views of a same image. However, traditional data augmentation may bring to the fore undesirable distortions on identity features, which is not always favorable in id-sensitive ReID tasks. In this paper, we propose to replace traditional data augmentation with a generative adversarial network (GAN) that is targeted to generate augmented views for contrastive learning. A 3D mesh guided person image generator is proposed to disentangle a person image into id-related and id-unrelated features. Deviating from previous GAN-based ReID methods that only work in id-unrelated space (pose and camera style), we conduct GAN-based augmentation on both id-unrelated and id-related features. We further propose specific contrastive losses to help our network learn invariance from id-unrelated and id-related augmentations. By jointly training the generative and the contrastive modules, our method achieves new state-of-the-art unsupervised person ReID performance on mainstream large-scale benchmarks
Fichier principal
Vignette du fichier
arxiv_TPAMI.pdf (5.29 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03931340 , version 1 (09-01-2023)

Identifiants

Citer

Hao Chen, Yaohui Wang, Benoit Lagadec, Antitza Dantcheva, Francois Bremond. Learning Invariance from Generated Variance for Unsupervised Person Re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, inPress, pp.1-15. ⟨10.1109/TPAMI.2022.3226866⟩. ⟨hal-03931340⟩
26 Consultations
17 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More