Scholarlink

<p>Continual person re-identification (CReID) aims to learn a unified model to cope with changing scenarios (e.g., from malls to streets and stations, etc). However, deploying the CReID model directly on unseen scenarios (which cannot be foreseen) outside the continual pipeline leads to a drop in generalization performance due to distribution shifts. In this paper, we design a meta learning paradigm with the seen and unseen domains to adapt the model to distribution shifts, where the unseen domains are produced by our carefully designed Domain Diversity (DD). Considering the knowledge encompassing both seen and unseen domains can fight against forgetting as well as improve generalization, we accumulate the learned and future knowledge corresponding to seen and unseen domains respectively through graph attention networks. Subsequently, we integrate the accumulated knowledge into meta learning steps to guide the training of the model, ensuring less forgetting and better generalization. Extensive experiments conducted on twelve datasets demonstrate the effectiveness of our method with superior performance in generalization and anti-forgetting. The code is available at <a href="https://github.com/DFLAG-NEU/MetaDD">https://github.com/DFLAG-NEU/MetaDD</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Domain diversity based meta learning for continual person re-identification

  • 期刊论文

  • 发表日期：

    2025年7月11日

查看全文
  • Zhaoshuo Liu,
  • Chaolu Feng,
  • Kun Yu,
  • Jiangdian Song,
  • Wei Li

摘要

Continual person re-identification (CReID) aims to learn a unified model to cope with changing scenarios (e.g., from malls to streets and stations, etc). However, deploying the CReID model directly on unseen scenarios (which cannot be foreseen) outside the continual pipeline leads to a drop in generalization performance due to distribution shifts. In this paper, we design a meta learning paradigm with the seen and unseen domains to adapt the model to distribution shifts, where the unseen domains are produced by our carefully designed Domain Diversity (DD). Considering the knowledge encompassing both seen and unseen domains can fight against forgetting as well as improve generalization, we accumulate the learned and future knowledge corresponding to seen and unseen domains respectively through graph attention networks. Subsequently, we integrate the accumulated knowledge into meta learning steps to guide the training of the model, ensuring less forgetting and better generalization. Extensive experiments conducted on twelve datasets demonstrate the effectiveness of our method with superior performance in generalization and anti-forgetting. The code is available at https://github.com/DFLAG-NEU/MetaDD.