A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Computer Vision and Image Understanding Année : 2022

A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification

Résumé

The use of pseudo-labels prevails to tackle Unsupervised Domain Adaptive (UDA) Re-Identification (re-ID) with the best performance. Indeed, this family of approaches has given rise to several UDA re-identification-specific frameworks, which are effective. In these works, research directions to improve Pseudo-Labeling UDA re-ID performance are varied and primarily based on intuition and experiments: refining pseudo-labels, reducing the impact of errors in pseudo-labels... It can be hard to deduce from them general good practices that we can implement in any Pseudo-Labeling method to improve its performance consistently. We propose a new theoretical view on Pseudo-Labeling UDA re-ID to address this fundamental question. The contributions are threefold: (i) A novel theoretical framework for Pseudo-Labeling UDA re-ID, formalized through a new general learning upper bound on the UDA re-ID performance. (ii) General good practices for Pseudo-Labeling are directly deduced from the interpretation of the proposed theoretical framework to improve the target re-ID performance. (iii) Extensive experiments on challenging person and vehicle cross-dataset re-ID tasks, showing consistent performance improvements for various state-of-the-art methods and various proposed implementations of good practices.
Fichier principal
Vignette du fichier
21761c2cd5bcc0364830f23747ba9e0e.pdf (4.26 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04125235 , version 1 (15-05-2024)

Identifiants

Citer

Fabian Dubourvieux, Romaric Audigier, Angélique Loesch, Samia Ainouz, Stéphane Canu. A formal approach to good practices in Pseudo-Labeling for Unsupervised Domain Adaptive Re-Identification. Computer Vision and Image Understanding, 2022, 223, pp.103527. ⟨10.1016/j.cviu.2022.103527⟩. ⟨hal-04125235⟩
13 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More