面向终身行人重识别的视觉-语言属性解耦与强化
Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification
把 VLM 的文本属性作为跨域共享的细粒度监督信号，用文本属性解耦+跨模态属性对齐来指导视觉特征提取，这一思路可直接迁移到其他需要抗遗忘的跨域检索/分类任务（如跨域行人检索、细粒度识别）中。
原文依据 introduces cross-modal attribute alignment to guide visual attribute extraction and adopts inter-domain attribute alignment to achieve fine-grained knowledge transfer
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论终身行人重识别（LReID）旨在从不断变化的域中学习，以获得统一的行人检索模型。现有的 LReID 方法通常从零开始学习，或基于视觉分类预训练模型进行学习，而视觉语言模型（VLM）已在多种任务中展现出可泛化的知识。尽管现有方法可以直接适配到 VLM 上，但由于它们只考虑全局感知学习，细粒度的属性知识未被充分利用，导致知识获取与抗遗忘能力有限。为解决这一问题，我们提出了一种新的由 VLM 驱动的 LReID 方法，名为视觉-语言属性解耦与强化（VLADR）。其核心思想是显式建模普遍共享的人体属性，以改善域间知识迁移，从而有效利用历史知识来强化新知识的学习并缓解遗忘。具体而言，VLADR 包含一个多粒度文本属性解耦机制，用于挖掘图像的全局文本属性与多样的局部文本属性。随后，我们设计了域间跨模态属性强化方案，引入跨模态属性对齐来指导视觉属性提取，并采用域间属性对齐来实现细粒度知识迁移。实验结果表明，VLADR 在抗遗忘能力和泛化能力上分别以 1.9%-2.2% 和 2.1%-2.5% 的优势优于最优方法。我们的源代码已发布于 https://github.com/zhoujiahuan1991/CVPR2026-VLADR。
英文原文摘要 1586 字符
Lifelong person re-identification (LReID) aims to learn from varying domains to obtain a unified person retrieval model. Existing LReID approaches typically focus on learning from scratch or a visual classification-pretrained model, while the Vision-Language Model (VLM) has shown generalizable knowledge in a variety of tasks. Although existing methods can be directly adapted to the VLM, since they only consider global-aware learning, the fine-grained attribute knowledge is underleveraged, leading to limited acquisition and anti-forgetting capacity. To address this problem, we introduce a novel VLM-driven LReID approach named Vision-Language Attribute Disentanglement and Reinforcement (VLADR). Our key idea is to explicitly model the universally shared human attributes to improve inter-domain knowledge transfer, thereby effectively utilizing historical knowledge to reinforce new knowledge learning and alleviate forgetting. Specifically, VLADR includes a Multi-grain Text Attribute Disentanglement mechanism that mines the global and diverse local text attributes of an image. Then, an Inter-domain Cross-modal Attribute Reinforcement scheme is developed, which introduces cross-modal attribute alignment to guide visual attribute extraction and adopts inter-domain attribute alignment to achieve fine-grained knowledge transfer. Experimental results demonstrate that our VLADR outperforms the state-of-the-art methods by 1.9%-2.2% and 2.1%-2.5% on anti-forgetting and generalization capacity. Our source code is available at https://github.com/zhoujiahuan1991/CVPR2026-VLADR