Image-Text-Image Knowledge Transfer for Lifelong Person Re-Identification with Hybrid Clothing States

TL;DR

This paper introduces a novel lifelong person re-identification framework that effectively handles clothing changes by aligning image and text knowledge in a closed loop, improving knowledge transfer and generalization.

Contribution

It proposes a new framework, $Teata$, that uses structured semantic prompts and knowledge adaptation to address clothing variability in lifelong person re-identification.

Findings

$Teata$ outperforms existing methods on LReID-Hybrid benchmarks.

Effective knowledge transfer reduces clothing change impact.

Framework maintains performance across different domains.

Abstract

With the continuous expansion of intelligent surveillance networks, lifelong person re-identification (LReID) has received widespread attention, pursuing the need of self-evolution across different domains. However, existing LReID studies accumulate knowledge with the assumption that people would not change their clothes. In this paper, we propose a more practical task, namely lifelong person re-identification with hybrid clothing states (LReID-Hybrid), which takes a series of cloth-changing and same-cloth domains into account during lifelong learning. To tackle the challenges of knowledge granularity mismatch and knowledge presentation mismatch in LReID-Hybrid, we take advantage of the consistency and generalization capabilities of the text space, and propose a novel framework, dubbed $Teata$, to effectively align, transfer, and accumulate knowledge in an "image-text-image" closed loop. Concretely, to achieve effective knowledge transfer, we design a Structured Semantic Prompt (SSP) learning to decompose the text prompt into several structured pairs to distill knowledge from the image space with a unified granularity of text description. Then, we introduce a Knowledge Adaptation and Projection (KAP) strategy, which tunes text knowledge via a slow-paced learner to adapt to different tasks without catastrophic forgetting. Extensive experiments demonstrate the superiority of our proposed $Teata$ for LReID-Hybrid as well as on conventional LReID benchmarks over advanced methods.