Online Unsupervised Domain Adaptation for Person Re-identification - Télécom Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Online Unsupervised Domain Adaptation for Person Re-identification

Hamza Rami
  • Fonction : Auteur
  • PersonId : 1375169
Matthieu Ospici
  • Fonction : Auteur

Résumé

Unsupervised domain adaptation for person re-identification (Person Re-ID) is the task of transferring the learned knowledge on the labeled source domain to the unlabeled target domain. Most of the recent papers that address this problem adopt an offline training setting. More precisely, the training of the Re-ID model is done assuming that we have access to the complete training target domain data set. In this paper, we argue that the target domain generally consists of a stream of data in a practical real-world application, where data is continuously increasing from the different network's cameras. The Re-ID solutions are also constrained by confidentiality regulations stating that the collected data can be stored for only a limited period, hence the model can no longer get access to previously seen target images. Therefore, we present a new yet practical online setting for Unsupervised Domain Adaptation for person Re-ID with two main constraints: Online Adaptation and Privacy Protection. We then adapt and evaluate the state-of-the-art UDA algorithms on this new online setting using the well-known Market-1501, Duke, and MSMT17 benchmarks.

Dates et versions

hal-04204997 , version 1 (12-09-2023)

Identifiants

Citer

Hamza Rami, Matthieu Ospici, Stéphane Lathuilière. Online Unsupervised Domain Adaptation for Person Re-identification. IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPR-W) on Continual Learning in Computer Vision, 2022, New orleans, USA, United States. ⟨hal-04204997⟩
4 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More