Abstract
Gait Recognition is a computer vision task aiming to identify people by their walking patterns. Existing methods show impressive results on individual datasets but 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. UDA for Gait Recognition is still in its infancy and existing works proposed solutions to limited scenarios. In this paper, we reveal a fundamental phenomenon in adaptation of gait recognition models, in which the target domain is biased to pose-based features rather than identity features, causing a significant performance drop in the identification task. We suggest Gait Orientation-based method for Unsupervised Domain Adaptation (GOUDA) to reduce this bias. To this end, we present a novel Triplet Selection algorithm with a curriculum learning framework, aiming to adapt the embedding space by pushing away samples of similar poses and bringing closer samples of different poses. 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, showing the superiority of our proposed method over prior works.
Abstract (translated)
步识别是计算机视觉任务,旨在通过步进模式识别人类。现有方法在个人数据集上表现出令人印象深刻的结果,但缺乏对未知场景的泛化能力。无监督领域适应(UDA)尝试适应在一个源领域中以监督方式训练过的模型,到未标记的目标领域。步识别领域的UDA仍然处于婴儿期,现有工作提出了针对有限场景的解决方案。在本文中,我们揭示了步识别模型适应中的基本概念现象,即目标领域受到姿态特征而不是身份特征的偏见,导致识别任务的性能大幅下降。我们建议步方向based方法(GOUDA)以降低这种偏见。为此,我们提出了一种新的三选一算法,结合课程学习框架,旨在通过推开相似姿态样本并使不同姿态样本更接近来适应嵌入空间。我们提供了广泛的实验,对四种广泛使用的步识别数据集、CASIA-B、OU-MVLP、GREW和Gait3D,以及对三个支柱、GaitSet、GaitPart和GaitGL,展示了我们提出的方法相对于先前工作的优势。
URL
https://arxiv.org/abs/2307.06751
