Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification

ArXi:2605.05027v1 Announce Type: new Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from semantic drift, limited adaptability, and catastrophic forgetting as new domains emerge. Existing exemplar-free approaches largely rely on visual-only distillation or parameter regularization, while overlooking the potential of auxiliary modalities, such as text, to preserve semantic stability and enable incremental plasticity.