RobustGait: Robustness Analysis for Appearance Based Gait Recognition

TL;DR

RobustGait provides a comprehensive framework for evaluating the robustness of appearance-based gait recognition systems against various real-world corruptions and silhouette extraction biases, revealing key factors affecting performance.

Contribution

It introduces a detailed robustness evaluation benchmark for gait recognition, analyzing multiple perturbation types, extraction methods, and model architectures, with strategies to enhance robustness.

Findings

RGB-level noise better reflects real-world degradation

Silhouette extractor biases significantly impact accuracy

Robustness varies with perturbation type and model design

Abstract

Appearance-based gait recognition have achieved strong performance on controlled datasets, yet systematic evaluation of its robustness to real-world corruptions and silhouette variability remains lacking. We present RobustGait, a framework for fine-grained robustness evaluation of appearance-based gait recognition systems. RobustGait evaluation spans four dimensions: the type of perturbation (digital, environmental, temporal, occlusion), the silhouette extraction method (segmentation and parsing networks), the architectural capacities of gait recognition models, and various deployment scenarios. The benchmark introduces 15 corruption types at 5 severity levels across CASIA-B, CCPG, and SUSTech1K, with in-the-wild validation on MEVID, and evaluates six state-of-the-art gait systems. We came across several exciting insights. First, applying noise at the RGB level better reflects real-world degradation, and reveal how distortions propagate through silhouette extraction to the downstream gait recognition systems. Second, gait accuracy is highly sensitive to silhouette extractor biases, revealing an overlooked source of benchmark bias. Third, robustness is dependent on both the type of perturbation and the architectural design. Finally, we explore robustness-enhancing strategies, showing that noise-aware training and knowledge distillation improve performance and move toward deployment-ready systems. Code is available at https://reeshoon.github.io/robustgaitbenchmark