Recent advances in person re-identification (ReID) obtain impressive accuracy in the supervised and unsupervised learning settings. However, most of the existing methods need to train a new model for a new domain by accessing data. Due to public privacy, the new domain data are not always accessible, leading to a limited applicability of these methods. In this paper, we study the problem of multi-source domain generalization in ReID, which aims to learn a model that can perform well on unseen domains with only several labeled source domains. To address this problem, we propose the Memory-based Multi-Source Meta-Learning ((ML)-L-3) framework to train a generalizable model for unseen domains. Specifically, a meta-learning strategy is introduced to simulate the train-test process of domain generalization for learning more generalizable models. To overcome the unstable meta-optimization caused by the parametric classifier, we propose a memory-based identification loss that is non-parametric and harmonizes with meta-learning. We also present a meta batch normalization layer (MetaBN) to diversify meta-test features, further establishing the advantage of meta-learning. Experiments demonstrate that our (ML)-L-3 can effectively enhance the generalization ability of the model for unseen domains and can outperform the state-of-the-art methods on four large-scale ReID datasets.

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification / Zhao, Yuyang; Zhong, Zhun; Yang, Fengxiang; Luo, Zhiming; Lin, Yaojin; Li, Shaozi; Sebe, Nicu. - (2021), pp. 6273-6282. (Intervento presentato al convegno CVPR 2021 tenutosi a virtual conference nel 20th-25th June 2021) [10.1109/CVPR46437.2021.00621].

Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification

Zhong, Zhun;Sebe, Nicu
2021-01-01

Abstract

Recent advances in person re-identification (ReID) obtain impressive accuracy in the supervised and unsupervised learning settings. However, most of the existing methods need to train a new model for a new domain by accessing data. Due to public privacy, the new domain data are not always accessible, leading to a limited applicability of these methods. In this paper, we study the problem of multi-source domain generalization in ReID, which aims to learn a model that can perform well on unseen domains with only several labeled source domains. To address this problem, we propose the Memory-based Multi-Source Meta-Learning ((ML)-L-3) framework to train a generalizable model for unseen domains. Specifically, a meta-learning strategy is introduced to simulate the train-test process of domain generalization for learning more generalizable models. To overcome the unstable meta-optimization caused by the parametric classifier, we propose a memory-based identification loss that is non-parametric and harmonizes with meta-learning. We also present a meta batch normalization layer (MetaBN) to diversify meta-test features, further establishing the advantage of meta-learning. Experiments demonstrate that our (ML)-L-3 can effectively enhance the generalization ability of the model for unseen domains and can outperform the state-of-the-art methods on four large-scale ReID datasets.
2021
Proceedings: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition
Piscataway, NJ
IEEE
978-1-6654-4509-2
Zhao, Yuyang; Zhong, Zhun; Yang, Fengxiang; Luo, Zhiming; Lin, Yaojin; Li, Shaozi; Sebe, Nicu
Learning to Generalize Unseen Domains via Memory-based Multi-Source Meta-Learning for Person Re-Identification / Zhao, Yuyang; Zhong, Zhun; Yang, Fengxiang; Luo, Zhiming; Lin, Yaojin; Li, Shaozi; Sebe, Nicu. - (2021), pp. 6273-6282. (Intervento presentato al convegno CVPR 2021 tenutosi a virtual conference nel 20th-25th June 2021) [10.1109/CVPR46437.2021.00621].
File in questo prodotto:
File Dimensione Formato  
Zhao_Learning_to_Generalize_Unseen_Domains_via_Memory-based_Multi-Source_Meta-Learning_for_CVPR_2021_paper.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.98 MB
Formato Adobe PDF
1.98 MB Adobe PDF Visualizza/Apri
Learning_to_Generalize_Unseen_Domains_via_Memory-based_Multi-Source_Meta-Learning_for_Person_Re-Identification.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.12 MB
Formato Adobe PDF
1.12 MB Adobe PDF   Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/326186
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 88
  • ???jsp.display-item.citation.isi??? 60
social impact