MimicGait: A Model Agnostic approach for Occluded Gait Recognition using Correlational Knowledge Distillation

TL;DR

MimicGait introduces a model-agnostic method for occluded gait recognition that leverages correlational knowledge distillation and an auxiliary visibility network to improve accuracy in challenging outdoor environments.

Contribution

It proposes a novel multi-instance correlational distillation approach combined with visibility estimation for occluded gait recognition, addressing a less-explored problem.

Findings

Effective on real-world datasets GREW, Gait3D, and BRIAR.

Outperforms existing methods in occluded gait recognition.

Demonstrates robustness to occlusions and environmental variations.

Abstract

Gait recognition is an important biometric technique over large distances. State-of-the-art gait recognition systems perform very well in controlled environments at close range. Recently, there has been an increased interest in gait recognition in the wild prompted by the collection of outdoor, more challenging datasets containing variations in terms of illumination, pitch angles, and distances. An important problem in these environments is that of occlusion, where the subject is partially blocked from camera view. While important, this problem has received little attention. Thus, we propose MimicGait, a model-agnostic approach for gait recognition in the presence of occlusions. We train the network using a multi-instance correlational distillation loss to capture both inter-sequence and intra-sequence correlations in the occluded gait patterns of a subject, utilizing an auxiliary Visibility Estimation Network to guide the training of the proposed mimic network. We demonstrate the effectiveness of our approach on challenging real-world datasets like GREW, Gait3D and BRIAR. We release the code in https://github.com/Ayush-00/mimicgait.