无需记忆回放和知识蒸馏，实现持续学习中的人体重识别
DSKC: Domain Style Modeling with Adaptive Knowledge Consolidation for Exemplar-free Lifelong Person Re-Identification
- 用动态域风格编码器捕捉不同摄像头的视觉风格差异
- 通过统一知识整合机制融合实例与域风格信息，提升抗遗忘能力
- 适合长期在线学习场景，尤其在新旧数据交替时表现优异
终身人体重识别（LReID）旨在从连续的数据流中跨摄像头持续匹配个体。现有方法常忽略域特定风格感知与统一知识整合，导致适应新信息时出现遗忘。本文提出DSKC，一种无需记忆回放和知识蒸馏的新型框架。DSKC设计了域风格编码器（DSE），用于动态建模域特定风格；并引入统一知识整合（UKC）机制，自适应地将实例级特征与域风格信息融合为跨域统一表示。通过该统一表示作为桥梁，显式建模实例与域间的关联，增强抗遗忘与泛化能力。实验表明，DSKC在两种训练顺序下均优于现有最优方法，显著提升模型性能。代码已开源：https://github.com/LiuShiBen/DKUA。
原文摘要 · Abstract (English)
Lifelong Person Re-identification (LReID) aims to continuously match individuals across camera views from sequential data streams. Existing LReID methods often ignore domain-specific style awareness and unified knowledge consolidation, which are crucial for mitigating forgetting when adapting to new information. We propose DSKC, a novel rehearsal-free and distillation-free framework for LReID. DSKC designs a domain-style encoder (DSE) to dynamically model domain-specific styles, and a unified knowledge consolidation (UKC) mechanism to adaptively integrate instance-level representations with domain-specific style into a cross-domain unified representation. By leveraging unified representation as a bridge, DSKC explicitly models inter-domain associations at both instance and domain levels to enhance anti-forgetting and generalization. Experimental results demonstrate that our DSKC outperforms state-of-the-art methods in two training orders and enhances the model's strong performance. Our code is available at https://github.com/LiuShiBen/DKUA.
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。