GaitMPL：基于记忆增强渐进式学习的步态识别
GaitMPL: Gait Recognition with Memory-Augmented Progressive Learning
AI总结：
针对步态识别中由协变量和剪影特性导致的难样本问题，提出含动态重加权渐进学习模块与全局结构对齐记忆库的GaitMPL网络，在CASIA-B等数据集上取得当前最优性能。
摘要：
步态识别旨在通过生物特征步态模式远距离识别行人。由于存在多种协变量，且剪影具有无纹理、无色彩的特性，该任务存在固有挑战，会产生两类成对难样本：同一行人可能拥有差异较大的剪影（类内多样性），不同行人可能拥有相似的剪影（类间相似性）。本研究提出记忆增强渐进式学习网络（GaitMPL）来解决难样本问题，该网络包含动态重加权渐进学习模块（DRPL）和全局结构对齐记忆库（GSAM）。具体而言，DRPL通过由易到难的渐进式学习降低难样本的学习难度；GSAM则通过结构对齐记忆机制进一步增强DRPL的性能，该机制可维护并建模每个身份（ID）的特征分布。在两个常用数据集CASIA-B和OU-MVLP上的实验验证了GaitMPL的有效性。在CASIA-B数据集上，我们取得了当前最优性能：在最具挑战性的条件（衣着变化）下准确率达88.0%，平均条件下准确率达93.3%，分别比其他方法至少高出3.8%和1.4%。
英文摘要：
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.
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。
