GaitKD：一种通用的解耦蒸馏框架用于高效的姿态识别
GaitKD: A Universal Decoupled Distillation Framework for Efficient Gait Recognition
AI总结：
本文提出GaitKD框架，通过解耦决策级和边界级蒸馏提升姿态识别性能，支持异构教师-学生模型，实验显示其优于现有基线。
摘要：
姿态识别是一种具有吸引力的生物特征模态，适用于远距离和无接触识别，但高性能姿态模型通常依赖深度且计算成本高的架构，难以实际部署。知识蒸馏（KD）提供了一种自然方式将知识从强大教师转移到高效学生；然而，标准KD在部分结构化姿态模型中效果较差，其中监督来自部分分类logits和部分检索嵌入。本文提出GaitKD，一种蒸馏框架，将姿态知识转移解耦为两个互补组件：决策级蒸馏和边界级蒸馏。具体而言，GaitKD通过部分校准logit蒸馏对齐教师和学生，以转移类间决策关系，同时通过激活边界目标保持嵌入空间的教师诱导分区，而非直接特征回归。通过简单的对齐部分设计，GaitKD支持异构教师-学生姿态模型，无需引入额外推理成本。在多个姿态识别基准和教师-学生配置上的实验结果表明，GaitKD在强姿态基线上表现出一致的改进。我们的研究证明，这两个转移组件是互补的，保持边界蒸馏比直接特征回归提供更稳定的性能。源代码可在https://github.com/liyiersan/GaitKD/获取。
英文摘要：
Gait recognition is an attractive biometric modality for long-range and contact-free identification, but high-performing gait models often rely on deep and computationally expensive architectures that are difficult to deploy in practice. Knowledge distillation (KD) offers a natural way to transfer knowledge from a powerful teacher to an efficient student; however, standard KD is often less effective for part-structured gait models, where supervision is formed from both part-wise classification logits and part-wise retrieval embeddings. In this paper, we propose GaitKD, a distillation framework that decouples gait knowledge transfer into two complementary components: decision-level distillation and boundary-level distillation. Specifically, GaitKD aligns the teacher and student through part-calibrated logit distillation to transfer inter-class decision relations, while preserving the teacher-induced partitioning of the embedding space through an activation-boundary objective instead of direct feature regression. With a simple aligned part-wise design, GaitKD supports heterogeneous teacher-student gait models without introducing additional inference cost. Experimental results across multiple gait recognition benchmarks and teacher-student configurations show consistent improvements over strong gait baselines. Our study demonstrates that the two transfer components are complementary, and boundary-preserving distillation provides more stable performance than direct feature regression. Source code is available at https://github.com/liyiersan/GaitKD/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
