解决衣物变化下持续学习的人体重识别问题，提升跨场景泛化能力。
Contextualized Multimodal Lifelong Person Re-Identification in Hybrid Clothing States
- 基于CLIP设计双任务框架，动态生成语义提示并融合多粒度视觉特征。
- 在多个数据集上实现最优性能，相比基线提升12.3%以上，对衣物变化鲁棒。
- 适合长期监控中需持续学习的场景，如智能安防、跨摄像头追踪。
人体重识别（ReID）在真实监控系统中面临衣物变化（CCReID）和持续学习（LReID）双重挑战。现有方法通常仅针对同衣（SC）场景或独立处理衣物变化问题。本文提出LReID-Hybrid任务，旨在构建同时应对SC与CC变化的持续学习模型。针对表征错配与任务遗忘问题，提出CMLReID框架，包含两项创新：（1）上下文感知语义提示（CASP），自适应生成提示并融合多粒度视觉线索与语义空间；（2）自适应知识融合与投影（AKFP），通过双路径学习器结合服装状态感知投影损失，生成鲁棒的SC/CC原型。在多个数据集上的实验表明，该方法显著优于现有最先进方法，在衣物变化和序列学习条件下均表现出强鲁棒性与泛化能力。
原文摘要 · Abstract (English)
Person Re-Identification (ReID) has several challenges in real-world surveillance systems due to clothing changes (CCReID) and the need for maintaining continual learning (LReID). Previous existing methods either develop models specifically for one application, which is mostly a same-cloth (SC) setting or treat CCReID as its own separate sub-problem. In this work, we will introduce the LReID-Hybrid task with the goal of developing a model to achieve both SC and CC while learning in a continual setting. Mismatched representations and forgetting from one task to the next are significant issues, we address this with CMLReID, a CLIP-based framework composed of two novel tasks: (1) Context-Aware Semantic Prompt (CASP) that generates adaptive prompts, and also incorporates context to align richly multi-grained visual cues with semantic text space; and (2) Adaptive Knowledge Fusion and Projection (AKFP) which produces robust SC/CC prototypes through the use of a dual-path learner that aligns features with our Clothing-State-Aware Projection Loss. Experiments performed on a wide range of datasets and illustrate that CMLReID outperforms all state-of-the-art methods with strong robustness and generalization despite clothing variations and a sophisticated process of sequential learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。