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

• URL: http://arxiv.org/abs/2605.05027v1
• Date: Wed, 06 May 2026 15:23:13 GMT
• Title: Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification
• Abstract summary: Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data.<n> Existing exemplar-free approaches largely rely on visual-only distillation or parameter regularization.<n>We propose Prompt-Anchored vision-text Distillation (PAD), an asymmetric vision-text framework for semantic alignment and cross-domain generalization.
• Score: 60.02530716177415
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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. We observe that the frozen text encoder in pretrained vision-language models can serve as a stable semantic anchor across domains. To decouple the roles of vision and text, we propose Prompt-Anchored vision-text Distillation (PAD), an asymmetric vision-text framework for semantic alignment and cross-domain generalization. On the textual side, we distill prompts to preserve vision-text alignment under a fixed semantic space, acting as a global semantic reference rather than a dominant learning signal. On the visual side, an EMA-based teacher with an adaptive prompt pool enables domain-wise adaptation by allocating new slots while freezing past ones. Extensive experiments show that PAD substantially outperforms state-of-the-art methods across seen and unseen domains, achieving a strong balance between stability and plasticity. Project page is available at https://github.com/zu-zi/PAD.

Related papers

• Continual Visual Learning under Evolving Semantic Concept Shift [1.565870461096057]
  SemReWrite is a framework for selectively updating obsolete visual-semantic mappings while preserving knowledge that remains valid.<n>We also introduce EvoShift-Bench, spanning ImageNet, iNaturalist, CUB-200-2011, and DomainNet, with semantic transitions including class split, merge, boundary revision, insertion, partial redefinition, recurrence, and mixed semantic-appearance shift.
  arXiv  Detail & Related papers  (2026-08-24T23:14:46Z)
• Towards Domain-Generalized Open-Vocabulary Object Detection: A Progressive Domain-invariant Cross-modal Alignment Method [59.30562121800656]
  Open-Vocabulary Object Detection has achieved remarkable success in generalizing to novel categories.<n>We provide a principled revisit of the OVOD paradigm, uncovering a fundamental vulnerability.<n>We propose Progressive Domain-invariant Cross-modal Alignment (PICA)
  arXiv  Detail & Related papers  (2026-03-29T07:39:31Z)
• Footprint-Guided Exemplar-Free Continual Histopathology Report Generation [3.361593315894868]
  We introduce an exemplar-free continual learning framework for WSI-to-report generation.<n>The core idea is a compact domain footprint built in a frozen patch-embedding space.<n>Our approach outperforms exemplar-free and limited-buffer rehearsal baselines.
  arXiv  Detail & Related papers  (2026-02-27T08:58:03Z)
• Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection [62.89126207012712]
  Face Presentation Attack Detection (PAD) demands incremental learning to combat spoofing tactics and domains.<n>Privacy regulations forbid retaining past data, necessitating rehearsal-free learning (RF-IL)
  arXiv  Detail & Related papers  (2025-12-22T04:30:11Z)
• Constrained Prompt Enhancement for Improving Zero-Shot Generalization of Vision-Language Models [57.357091028792325]
  Vision-language models (VLMs) pre-trained on web-scale data exhibit promising zero-shot generalization but often suffer from semantic misalignment.<n>We propose a novel constrained prompt enhancement (CPE) method to improve visual-textual alignment.<n>Our approach consists of two key components: Topology-Guided Synonymous Semantic Generation (TGSSG) and Category-Agnostic Discriminative Region Selection (CADRS)
  arXiv  Detail & Related papers  (2025-08-24T15:45:22Z)
• Harnessing Textual Semantic Priors for Knowledge Transfer and Refinement in CLIP-Driven Continual Learning [47.56496248878093]
  Continual learning aims to equip models with the ability to learn from a stream of tasks without forgetting previous knowledge.<n>We propose a unified framework that harnesses the anti-forgetting and structured nature of textual priors to guide semantic-aware knowledge transfer.
  arXiv  Detail & Related papers  (2025-08-03T04:09:00Z)
• Prompt Disentanglement via Language Guidance and Representation Alignment for Domain Generalization [75.88719716002014]
  Domain Generalization (DG) seeks to develop a versatile model capable of performing effectively on unseen target domains.<n>Recent advances in pre-trained Visual Foundation Models (VFMs) have demonstrated considerable potential in enhancing the generalization capabilities of deep learning models.<n>We propose addressing this challenge by leveraging the controllable and flexible language prompt of the VFM.
  arXiv  Detail & Related papers  (2025-07-03T03:52:37Z)
• Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification [30.782126710974165]
  Lifelong person re-identification attempts to recognize people across cameras and integrate new knowledge from continuous data streams. Key challenges involve addressing catastrophic forgetting caused by parameter updating and domain shift. We propose using textual descriptions as guidance to encourage the ReID model to learn cross-domain invariant features without retaining samples.
  arXiv  Detail & Related papers  (2024-11-09T00:57:19Z)
• Fine-Grained Semantically Aligned Vision-Language Pre-Training [151.7372197904064]
  Large-scale vision-language pre-training has shown impressive advances in a wide range of downstream tasks. Existing methods mainly model the cross-modal alignment by the similarity of the global representations of images and texts. We introduce LO, a fine-grained semantically aLigned visiOn-langUage PrE-training framework, which learns fine-grained semantic alignment from the novel perspective of game-theoretic interactions.
  arXiv  Detail & Related papers  (2022-08-04T07:51:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.