In this paper, we introduce a challenging yet practical setting for person re-identification (ReID) task, named lifelong person re-identification (LReID), which aims to continuously train a ReID model across multiple domains and the trained model is required to generalize well on both seen and unseen domains. It is therefore critical to learn a ReID model that can learn a generalized representation without forgetting knowledge of seen domains. In this paper, we propose a new MEmorizing and GEneralizing framework (MEGE) for LReID, which can jointly prevent the model from forgetting and improve its generalization ability. Specifically, our MEGE is composed of two novel modules, i.e., Adaptive Knowledge Accumulation (AKA) and differentiable Ranking Consistency Distillation (RCD). Taking inspiration from the cognitive processes in the human brain, we endow AKA with two special capacities, knowledge representation and knowledge operation by graph convolution networks. AKA can effectively mitigate catastrophic forgetting on seen domains while improving the generalization ability to unseen domains. By considering the ranking factor that is specifically important in ReID, RCD is designed to distill the ranking knowledge in a differentiable manner, which can further prevent the catastrophic forgetting. To supporting the study of LReID, we build a new and large-scale benchmark with two practical evaluation protocols that consider the metrics of non-forgetting and generalization. Experiments demonstrate that 1) our MEGE framework can effectively improve the performance on seen and unseen domains under the domain-incremental learning constraint, and that 2) the proposed MEGE outperforms state-of-the-art competitors by large margins.

A Memorizing and Generalizing Framework for Lifelong Person Re-Identification / Pu, N.; Zhong, Z.; Sebe, N.; Lew, M. S.. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 45:11(2023), pp. 13567-13585. [10.1109/TPAMI.2023.3297058]

A Memorizing and Generalizing Framework for Lifelong Person Re-Identification

Pu, N.;Zhong, Z.;Sebe, N.;
2023-01-01

Abstract

In this paper, we introduce a challenging yet practical setting for person re-identification (ReID) task, named lifelong person re-identification (LReID), which aims to continuously train a ReID model across multiple domains and the trained model is required to generalize well on both seen and unseen domains. It is therefore critical to learn a ReID model that can learn a generalized representation without forgetting knowledge of seen domains. In this paper, we propose a new MEmorizing and GEneralizing framework (MEGE) for LReID, which can jointly prevent the model from forgetting and improve its generalization ability. Specifically, our MEGE is composed of two novel modules, i.e., Adaptive Knowledge Accumulation (AKA) and differentiable Ranking Consistency Distillation (RCD). Taking inspiration from the cognitive processes in the human brain, we endow AKA with two special capacities, knowledge representation and knowledge operation by graph convolution networks. AKA can effectively mitigate catastrophic forgetting on seen domains while improving the generalization ability to unseen domains. By considering the ranking factor that is specifically important in ReID, RCD is designed to distill the ranking knowledge in a differentiable manner, which can further prevent the catastrophic forgetting. To supporting the study of LReID, we build a new and large-scale benchmark with two practical evaluation protocols that consider the metrics of non-forgetting and generalization. Experiments demonstrate that 1) our MEGE framework can effectively improve the performance on seen and unseen domains under the domain-incremental learning constraint, and that 2) the proposed MEGE outperforms state-of-the-art competitors by large margins.
2023
11
Pu, N.; Zhong, Z.; Sebe, N.; Lew, M. S.
A Memorizing and Generalizing Framework for Lifelong Person Re-Identification / Pu, N.; Zhong, Z.; Sebe, N.; Lew, M. S.. - In: IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE. - ISSN 0162-8828. - 45:11(2023), pp. 13567-13585. [10.1109/TPAMI.2023.3297058]
File in questo prodotto:
File Dimensione Formato  
Nan-PAMI2023.pdf

accesso aperto

Tipologia: Post-print referato (Refereed author’s manuscript)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 3.71 MB
Formato Adobe PDF
3.71 MB Adobe PDF Visualizza/Apri
A_Memorizing_and_Generalizing_Framework_for_Lifelong_Person_Re-Identification.pdf

Solo gestori archivio

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 4.47 MB
Formato Adobe PDF
4.47 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/11572/397897
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact