GaitMPL: Gait Recognition with Memory-Augmented Progressive Learning

TL;DR

This paper introduces GaitMPL, a novel gait recognition method that employs memory-augmented progressive learning to effectively handle intra- and inter-class variations, achieving state-of-the-art results on standard datasets.

Contribution

GaitMPL combines progressive learning with a memory-augmented structure to improve gait recognition accuracy under challenging conditions.

Findings

Achieves 88.0% accuracy on CASIA-B Clothing condition.

Outperforms previous methods by at least 3.8%.

Demonstrates effectiveness on CASIA-B and OU-MVLP datasets.

Abstract

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.