GaitAdapt: Continual Learning for Evolving Gait Recognition

TL;DR

GaitAdapt introduces a continual learning framework for gait recognition that preserves previous knowledge while adapting to new data, using graph neural networks and a stability method to improve recognition accuracy over time.

Contribution

The paper proposes GaitAdapter, a novel non-replay continual learning method for gait recognition, incorporating graph neural networks and a stability technique to enhance knowledge retention.

Findings

GaitAdapter outperforms existing methods in retaining gait recognition capabilities.

The approach effectively maintains discriminability across multiple tasks.

Extensive evaluations confirm the superiority of GaitAdapter in continual learning scenarios.

Abstract

Current gait recognition methodologies generally necessitate retraining when encountering new datasets. Nevertheless, retrained models frequently encounter difficulties in preserving knowledge from previous datasets, leading to a significant decline in performance on earlier test sets. To tackle these challenges, we present a continual gait recognition task, termed GaitAdapt, which supports the progressive enhancement of gait recognition capabilities over time and is systematically categorized according to various evaluation scenarios. Additionally, we propose GaitAdapter, a non-replay continual learning approach for gait recognition. This approach integrates the GaitPartition Adaptive Knowledge (GPAK) module, employing graph neural networks to aggregate common gait patterns from current data into a repository constructed from graph vectors. Subsequently, this repository is used to improve the discriminability of gait features in new tasks, thereby enhancing the model's ability to effectively recognize gait patterns. We also introduce a Euclidean Distance Stability Method (EDSN) based on negative pairs, which ensures that newly added gait samples from different classes maintain similar relative spatial distributions across both previous and current gait tasks, thereby alleviating the impact of task changes on the distinguishability of original domain features. Extensive evaluations demonstrate that GaitAdapter effectively retains gait knowledge acquired from diverse tasks, exhibiting markedly superior discriminative capability compared to alternative methods.