发表机构
Beijing Normal University; The University of Texas at Arlington（北京师范大学; 德克萨斯大学阿灵顿分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对步态识别中语义不一致和均匀性问题，提出基于扩散模型思想的Origins框架，通过统一模板的生成与表示联合学习，在多个基准数据集上取得优越性能。
AI 中文摘要
“我不能创造的东西，我就不理解。”人类的智慧揭示，创造是最高形式的学习之一。例如，扩散模型在图像生成、理解和修复中展现了显著的语义结构和记忆能力，这直观上有益于表示学习。然而，当前的步态网络很少采纳这一视角，主要依赖于在复杂多变条件下对比步态样本来进行学习，导致语义不一致和均匀性问题。为解决这些问题，我们提出了具有生成能力的Origins，其基本理念是不同实体由统一模板生成，内在将步态表示规范到一个一致且多样的语义空间中，以捕捉准确的步态差异。诚然，学习这一统一模板极具挑战性，因为它要求模板的全面性以涵盖各种条件下的步态表示。受扩散模型启发，Origins将统一模板扩散为时间步模板用于步态生成学习，同时将统一模板迁移用于步态表示学习。特别是，步态生成和表示学习作为一个统一框架进行端到端联合训练。在CASIA-B、CCPG、SUSTech1K、Gait3D、GREW和CCGR-MINI上的大量实验表明，Origins执行统一的生成和表示学习，实现了优越的性能。
英文摘要
"What I cannot create, I do not understand."Human wisdom reveals that creation is one of the highest forms of learning. For example, Diffusion Models have demonstrated remarkable semantic structure and memory in image generation, understanding, and restoration, which intuitively benefits representation learning. However, current gait networks rarely embrace this perspective, relying primarily on learning by contrasting gait samples under varying complex conditions, leading to semantic inconsistency and uniformity issues. To address these issues, we propose Origins with generative capabilities whose underlying philosophy is that different entities are generated from a unified template, inherently regularizing gait representations within a consistent and diverse semantic space to capture accurate gait differences. Admittedly, learning this unified template is exceedingly challenging, as it requires the comprehensiveness of the template to encompass gait representations with various conditions. Inspired by Diffusion Models, Origins diffuses the unified template into timestep templates for gait generative learning, and meanwhile transfers the unified template for gait representation learning. Especially, gait generative and representation learning serve as a unified framework for end-to-end joint training. Extensive experiments on CASIA-B, CCPG,SUSTech1K, Gait3D, GREW and CCGR-MINI demonstrate that Origins performs unified generative and representation learning, achieving superior performance.
CommentsAccepted at ICCV 2025
DOI：10.1109/ICCV51701.2025.01158
