Distillation-guided Representation Learning for Unconstrained Gait Recognition

TL;DR

This paper introduces GADER, a gait recognition framework that effectively identifies individuals in outdoor, unconstrained environments by leveraging silhouette and RGB data during training, with significant improvements over existing methods.

Contribution

GADER employs a novel Double Helical Signature for gait detection, encodes viewpoint information, and distills features from RGB models to enhance silhouette-based recognition in challenging scenarios.

Findings

Achieves 25.2% improvement on remote gait data.

Outperforms state-of-the-art methods in outdoor scenarios.

Demonstrates robustness across indoor and outdoor datasets.

Abstract

Gait recognition holds the promise of robustly identifying subjects based on walking patterns instead of appearance information. While previous approaches have performed well for curated indoor data, they tend to underperform in unconstrained situations, e.g. in outdoor, long distance scenes, etc. We propose a framework, termed GAit DEtection and Recognition (GADER), for human authentication in challenging outdoor scenarios. Specifically, GADER leverages a Double Helical Signature to detect segments that contain human movement and builds discriminative features through a novel gait recognition method, where only frames containing gait information are used. To further enhance robustness, GADER encodes viewpoint information in its architecture, and distills representation from an auxiliary RGB recognition model, which enables GADER to learn from silhouette and RGB data at training time. At test time, GADER only infers from the silhouette modality. We evaluate our method on multiple State-of-The-Arts(SoTA) gait baselines and demonstrate consistent improvements on indoor and outdoor datasets, especially with a significant 25.2% improvement on unconstrained, remote gait data.