Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters

Fabian Dubourvieux (1, 2) , Angélique Loesch (3) , Romaric Audigier (1, 4) , Samia Ainouz (5) , Stéphane Canu (6)

1 DIASI (CEA, LIST) - Département Intelligence Ambiante et Systèmes Interactifs
2 LITIS - Laboratoire d'Informatique, du Traitement de l'Information et des Systèmes
3 LVIC - Laboratoire Vision et Ingénierie des Contenus
4 LIST (CEA) - Laboratoire d'Intégration des Systèmes et des Technologies
5 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
6 DocApp - LITIS - Equipe Apprentissage

Unsupervised Domain Adaptation (UDA) for re-identification (re-ID) is a challenging task: to avoid a costly annotation of additional data, it aims at transferring knowledge from a domain with annotated data to a domain of interest with only unlabeled data. Pseudo-labeling approaches have proven to be effective for UDA re-ID. However, the effectiveness of these approaches heavily depends on the choice of some hyperparameters (HP) that affect the generation of pseudo-labels by clustering. The lack of annotation in the domain of interest makes this choice non-trivial. Current approaches simply reuse the same empirical value for all adaptation tasks and regardless of the target data representation that changes through pseudo-labeling training phases. As this simplistic choice may limit their performance, we aim at addressing this issue. We propose new theoretical grounds on HP selection for clustering UDA re-ID as well as method of automatic and cyclic HP tuning for pseudo-labeling UDA clustering: HyPASS. HyPASS consists in incorporating two modules in pseudo-labeling methods: (i) HP selection based on a labeled source validation set and (ii) conditional domain alignment of feature discriminativeness to improve HP selection based on source samples. Experiments on commonly used person re-ID and vehicle re-ID datasets show that our proposed HyPASS consistently improves the best state-of-the-art methods in re-ID compared to the commonly used empirical HP setting.

Mots clés: hyperparameter tuning object re-identification pseudo-labeling unsupervised domain adaptation; hyperparameter tuning; object re-identification; pseudo-labeling; unsupervised domain adaptation

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]

Fabian Dubourvieux, Angélique Loesch, Romaric Audigier, Samia Ainouz, Stéphane Canu. Improving Unsupervised Domain Adaptive Re-Identification via Source-Guided Selection of Pseudo-Labeling Hyperparameters. IEEE Access, 2021, 9, pp.149780-149795. ⟨10.1109/ACCESS.2017.DOI⟩. ⟨hal-04327854⟩