利用有限数据集提升步态识别的泛化性
Improving the generalization of gait recognition with limited datasets
AI总结：
针对混合数据集步态训练存在的监督冲突、样本冗余噪声问题，本文提出跨数据集步态学习统一范式，通过数据筛选与解耦度量学习，在不修改架构、无需额外标注的前提下提升步态识别跨域泛化性。
摘要：
由于视角、外观与环境存在显著域偏移，泛化步态识别仍面临挑战。混合数据集训练近期成为提升跨域鲁棒性的实用路径，但该方法存在两类尚未充分探索的问题：一是数据集间监督冲突，会干扰身份特征学习；二是冗余或噪声样本，会降低数据效率，还可能强化数据集专属模式。为解决上述挑战，本文提出一种跨数据集步态学习统一范式，可同时提升运动信号质量与监督一致性。首先，在表征冗余度与预测不确定性的引导下，抑制以冗余步态周期或不稳定轮廓为主的序列，提升训练数据可靠性，该数据优化步骤可在混合异构数据集时，将学习重点聚焦于信息丰富的步态动态。同时，通过解耦跨数据集的度量学习稳定监督过程，在每个源数据集内构建三元组，在保留可迁移身份线索的同时，避免产生破坏性的跨域梯度。上述组件协同作用，无需修改网络架构或额外标注即可稳定优化过程、增强泛化能力。在CASIA-B、OU-MVLP、Gait3D、GREW数据集上，采用GaitBase与DeepGaitV2骨干网络开展的实验一致表明，该方法在不损失域内精度的前提下提升了跨域性能，证明数据选择与监督对齐可有效实现可扩展的混合数据集步态学习。
英文摘要：
Generalized gait recognition remains challenging due to significant domain shifts in viewpoints, appearances, and environments. Mixed-dataset training has recently become a practical route to improve cross-domain robustness, but it introduces underexplored issues: 1) inter-dataset supervision conflicts, which distract identity learning, and 2) redundant or noisy samples, which reduce data efficiency and may reinforce dataset-specific patterns. To address these challenges, we introduce a unified paradigm for cross-dataset gait learning that simultaneously improves motion-signal quality and supervision consistency. We first increase the reliability of training data by suppressing sequences dominated by redundant gait cycles or unstable silhouettes, guided by representation redundancy and prediction uncertainty. This refinement concentrates learning on informative gait dynamics when mixing heterogeneous datasets. In parallel, we stabilize supervision by disentangling metric learning across datasets, forming triplets within each source to prevent destructive cross-domain gradients while preserving transferable identity cues. These components act in synergy to stabilize optimization and strengthen generalization without modifying network architectures or requiring extra annotations. Experiments on CASIA-B, OU-MVLP, Gait3D, and GREW with both GaitBase and DeepGaitV2 backbones consistently show improved cross-domain performance without sacrificing in-domain accuracy. These results demonstrate that data selection and aligning supervision effectively enables scalable mixed-dataset gait learning.
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。
