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

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 b...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Fabian Dubourvieux, Angelique Loesch, Romaric Audigier, Samia Ainouz, Stephane Canu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Hyperparameter tuning object re-identification pseudo-labeling unsupervised domain adaptation Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/9f9a58fc2f7844938f3124d1c93c897f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9f9a58fc2f7844938f3124d1c93c897f
record_format	dspace
spelling	oai:doaj.org-article:9f9a58fc2f7844938f3124d1c93c897f2021-11-18T00:02:13ZImproving Unsupervised Domain Adaptive Re-Identification Via Source-Guided Selection of Pseudo-Labeling Hyperparameters2169-353610.1109/ACCESS.2021.3124678https://doaj.org/article/9f9a58fc2f7844938f3124d1c93c897f2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9597556/https://doaj.org/toc/2169-3536Unsupervised 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.Fabian DubourvieuxAngelique LoeschRomaric AudigierSamia AinouzStephane CanuIEEEarticleHyperparameter tuningobject re-identificationpseudo-labelingunsupervised domain adaptationElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 149780-149795 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Hyperparameter tuning object re-identification pseudo-labeling unsupervised domain adaptation Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Hyperparameter tuning object re-identification pseudo-labeling unsupervised domain adaptation Electrical engineering. Electronics. Nuclear engineering TK1-9971 Fabian Dubourvieux Angelique Loesch Romaric Audigier Samia Ainouz Stephane Canu Improving Unsupervised Domain Adaptive Re-Identification Via Source-Guided Selection of Pseudo-Labeling Hyperparameters
description	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.
format	article
author	Fabian Dubourvieux Angelique Loesch Romaric Audigier Samia Ainouz Stephane Canu
author_facet	Fabian Dubourvieux Angelique Loesch Romaric Audigier Samia Ainouz Stephane Canu
author_sort	Fabian Dubourvieux
title	Improving Unsupervised Domain Adaptive Re-Identification Via Source-Guided Selection of Pseudo-Labeling Hyperparameters
title_short	Improving Unsupervised Domain Adaptive Re-Identification Via Source-Guided Selection of Pseudo-Labeling Hyperparameters
title_full	Improving Unsupervised Domain Adaptive Re-Identification Via Source-Guided Selection of Pseudo-Labeling Hyperparameters
title_fullStr	Improving Unsupervised Domain Adaptive Re-Identification Via Source-Guided Selection of Pseudo-Labeling Hyperparameters
title_full_unstemmed	Improving Unsupervised Domain Adaptive Re-Identification Via Source-Guided Selection of Pseudo-Labeling Hyperparameters
title_sort	improving unsupervised domain adaptive re-identification via source-guided selection of pseudo-labeling hyperparameters
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/9f9a58fc2f7844938f3124d1c93c897f
work_keys_str_mv	AT fabiandubourvieux improvingunsuperviseddomainadaptivereidentificationviasourceguidedselectionofpseudolabelinghyperparameters AT angeliqueloesch improvingunsuperviseddomainadaptivereidentificationviasourceguidedselectionofpseudolabelinghyperparameters AT romaricaudigier improvingunsuperviseddomainadaptivereidentificationviasourceguidedselectionofpseudolabelinghyperparameters AT samiaainouz improvingunsuperviseddomainadaptivereidentificationviasourceguidedselectionofpseudolabelinghyperparameters AT stephanecanu improvingunsuperviseddomainadaptivereidentificationviasourceguidedselectionofpseudolabelinghyperparameters
_version_	1718425241292636160

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

Ejemplares similares