IEEE Trans Image Process. 2024;33:1464-1475. doi: 10.1109/TIP.2022.3164543. Epub 2024 Feb 23.
Gait recognition aims at identifying the pedestrians at a long distance by their biometric gait patterns. It is inherently challenging due to the various covariates and the properties of silhouettes (textureless and colorless), which result in two kinds of pair-wise hard samples: the same pedestrian could have distinct silhouettes (intra-class diversity) and different pedestrians could have similar silhouettes (inter-class similarity). In this work, we propose to solve the hard sample issue with a Memory-augmented Progressive Learning network (GaitMPL), including Dynamic Reweighting Progressive Learning module (DRPL) and Global Structure-Aligned Memory bank (GSAM). Specifically, DRPL reduces the learning difficulty of hard samples by easy-to-hard progressive learning. GSAM further augments DRPL with a structure-aligned memory mechanism, which maintains and models the feature distribution of each ID. Experiments on two commonly used datasets, CASIA-B and OU-MVLP, demonstrate the effectiveness of GaitMPL. On CASIA-B, we achieve the state-of-the-art performance, i.e., 88.0% on the most challenging condition (Clothing) and 93.3% on the average condition, which outperforms the other methods by at least 3.8% and 1.4%, respectively. Code will be available at https://github.com/WhiteDOU/GaitMPL https://github.com/WhiteDOU/GaitMPL.
步态识别旨在通过生物特征步态模式识别远距离的行人。由于各种协变量和轮廓的特性（无纹理和无色），导致出现了两种成对的困难样本：同一个行人可能有明显不同的轮廓（类内多样性），而不同的行人可能有相似的轮廓（类间相似性），这使得步态识别具有挑战性。在这项工作中，我们提出了一种基于记忆增强渐进学习网络（GaitMPL）的方法来解决困难样本问题，包括动态加权渐进学习模块（DRPL）和全局结构对齐记忆库（GSAM）。具体来说，DRPL 通过从易到难的渐进学习来降低困难样本的学习难度。GSAM 进一步通过结构对齐的记忆机制来增强 DRPL，该机制可以保持和建模每个 ID 的特征分布。在两个常用的数据集 CASIA-B 和 OU-MVLP 上的实验证明了 GaitMPL 的有效性。在 CASIA-B 上，我们实现了最先进的性能，即在最具挑战性的条件（服装）下达到 88.0%，在平均条件下达到 93.3%，分别比其他方法至少高出 3.8%和 1.4%。代码将在 https://github.com/WhiteDOU/GaitMPL 上可用。
