Source-Guided Similarity Preservation for Online Person Re-Identification - Equipe Multimédia
Communication Dans Un Congrès Année : 2024

Source-Guided Similarity Preservation for Online Person Re-Identification

Résumé

Online Unsupervised Domain Adaptation (OUDA) for person Re-Identification (Re-ID) is the task of continuously adapting a model trained on a well-annotated source-domain dataset to a target domain observed as a data stream. In OUDA, person Re-ID models face two main challenges: catastrophic forgetting and domain shift. In this work, we propose a new Source-guided Similarity Preservation (S2P) framework to alleviate these two problems. Our framework is based on the extraction of a support set composed of source images that maximizes the similarity with the target data. This support set is used to identify feature similarities that must be preserved during the learning process. S2P can incorporate multiple existing UDA methods to mitigate catastrophic forgetting. Our experiments show that S2P outperforms previous state-of-the-art methods on multiple real-to-real and synthetic-to-real challenging OUDA benchmarks.
Fichier principal
Vignette du fichier
WACV_2024.pdf (2.39 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04541703 , version 1 (11-04-2024)

Identifiants

Citer

Hamza Rami, Jhony H. Giraldo, Nicolas Winckler, Stéphane Lathuilière. Source-Guided Similarity Preservation for Online Person Re-Identification. 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2024, Waikoloa, United States. pp.1700-1709, ⟨10.1109/WACV57701.2024.00173⟩. ⟨hal-04541703⟩
90 Consultations
67 Téléchargements

Altmetric

Partager

More