CFReID: Continual Few-shot Person Re-Identification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ni, Hao, Gao, Lianli, Zeng, Pengpeng, Shen, Heng Tao, Song, Jingkuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911250758238208
author Ni, Hao
Gao, Lianli
Zeng, Pengpeng
Shen, Heng Tao
Song, Jingkuan
author_facet Ni, Hao
Gao, Lianli
Zeng, Pengpeng
Shen, Heng Tao
Song, Jingkuan
contents Real-world surveillance systems are dynamically evolving, requiring a person Re-identification model to continuously handle newly incoming data from various domains. To cope with these dynamics, Lifelong ReID (LReID) has been proposed to learn and accumulate knowledge across multiple domains incrementally. However, LReID models need to be trained on large-scale labeled data for each unseen domain, which are typically inaccessible due to privacy and cost concerns. In this paper, we propose a new paradigm called Continual Few-shot ReID (CFReID), which requires models to be incrementally trained using few-shot data and tested on all seen domains. Under few-shot conditions, CFREID faces two core challenges: 1) learning knowledge from few-shot data of unseen domain, and 2) avoiding catastrophic forgetting of seen domains. To tackle these two challenges, we propose a Stable Distribution Alignment (SDA) framework from feature distribution perspective. Specifically, our SDA is composed of two modules, i.e., Meta Distribution Alignment (MDA) and Prototype-based Few-shot Adaptation (PFA). To support the study of CFReID, we establish an evaluation benchmark for CFReID on five publicly available ReID datasets. Extensive experiments demonstrate that our SDA can enhance the few-shot learning and anti-forgetting capabilities under few-shot conditions. Notably, our approach, using only 5\% of the data, i.e., 32 IDs, significantly outperforms LReID's state-of-the-art performance, which requires 700 to 1,000 IDs.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18469
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CFReID: Continual Few-shot Person Re-Identification
Ni, Hao
Gao, Lianli
Zeng, Pengpeng
Shen, Heng Tao
Song, Jingkuan
Computer Vision and Pattern Recognition
Real-world surveillance systems are dynamically evolving, requiring a person Re-identification model to continuously handle newly incoming data from various domains. To cope with these dynamics, Lifelong ReID (LReID) has been proposed to learn and accumulate knowledge across multiple domains incrementally. However, LReID models need to be trained on large-scale labeled data for each unseen domain, which are typically inaccessible due to privacy and cost concerns. In this paper, we propose a new paradigm called Continual Few-shot ReID (CFReID), which requires models to be incrementally trained using few-shot data and tested on all seen domains. Under few-shot conditions, CFREID faces two core challenges: 1) learning knowledge from few-shot data of unseen domain, and 2) avoiding catastrophic forgetting of seen domains. To tackle these two challenges, we propose a Stable Distribution Alignment (SDA) framework from feature distribution perspective. Specifically, our SDA is composed of two modules, i.e., Meta Distribution Alignment (MDA) and Prototype-based Few-shot Adaptation (PFA). To support the study of CFReID, we establish an evaluation benchmark for CFReID on five publicly available ReID datasets. Extensive experiments demonstrate that our SDA can enhance the few-shot learning and anti-forgetting capabilities under few-shot conditions. Notably, our approach, using only 5\% of the data, i.e., 32 IDs, significantly outperforms LReID's state-of-the-art performance, which requires 700 to 1,000 IDs.
title CFReID: Continual Few-shot Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.18469