Watch Where You Head: A View-biased Domain Gap in Gait Recognition and Unsupervised Adaptation
This addresses a domain gap issue in gait recognition for surveillance and biometric applications, offering an incremental improvement over prior unsupervised domain adaptation methods.
The paper tackles the problem of gait recognition models failing to generalize due to view bias in target domains, and proposes GOUDA, a method that reduces this bias and achieves state-of-the-art performance across multiple datasets and backbones.
Gait Recognition is a computer vision task aiming to identify people by their walking patterns. Although existing methods often show high performance on specific datasets, they lack the ability to generalize to unseen scenarios. Unsupervised Domain Adaptation (UDA) tries to adapt a model, pre-trained in a supervised manner on a source domain, to an unlabelled target domain. There are only a few works on UDA for gait recognition proposing solutions to limited scenarios. In this paper, we reveal a fundamental phenomenon in adaptation of gait recognition models, caused by the bias in the target domain to viewing angle or walking direction. We then suggest a remedy to reduce this bias with a novel triplet selection strategy combined with curriculum learning. To this end, we present Gait Orientation-based method for Unsupervised Domain Adaptation (GOUDA). We provide extensive experiments on four widely-used gait datasets, CASIA-B, OU-MVLP, GREW, and Gait3D, and on three backbones, GaitSet, GaitPart, and GaitGL, justifying the view bias and showing the superiority of our proposed method over prior UDA works.