MimicGait: A Model Agnostic approach for Occluded Gait Recognition using Correlational Knowledge Distillation
This addresses occlusion issues in gait recognition for biometric applications in uncontrolled settings, representing an incremental improvement over existing methods.
The paper tackled the problem of gait recognition under occlusion in real-world environments by proposing MimicGait, a model-agnostic approach using correlational knowledge distillation, achieving state-of-the-art performance on datasets like GREW, Gait3D, and BRIAR.
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.