论文标题
从室内到室外：无监督的域自适应步态识别
From Indoor To Outdoor: Unsupervised Domain Adaptive Gait Recognition
论文作者
论文摘要
步态识别是一项重要的AI任务，随着深度学习的发展，它已经迅速发展。但是，现有的基于学习的步态识别方法主要集中于单个领域，尤其是受限的实验室环境。在本文中，我们研究了一个无监督的域自适应步态识别（UDA-GR）的新问题，该问题在室内场景（源域）中学习带有监督标签的步态标识符，并应用于室外野外场景（目标域）。为此，我们开发了基于不确定性估计和基于正则化的UDA-GR方法。具体而言，我们研究了室内和室外场景中步态的特征，用于估计步态样品不确定性，该步态不确定性用于目标域的无监督微调，以减轻伪标签的噪声。我们还为提出的问题建立了一个新的基准，该基准显示了所提出的方法的有效性。我们将向公众发布这项工作中的基准和源代码。
Gait recognition is an important AI task, which has been progressed rapidly with the development of deep learning. However, existing learning based gait recognition methods mainly focus on the single domain, especially the constrained laboratory environment. In this paper, we study a new problem of unsupervised domain adaptive gait recognition (UDA-GR), that learns a gait identifier with supervised labels from the indoor scenes (source domain), and is applied to the outdoor wild scenes (target domain). For this purpose, we develop an uncertainty estimation and regularization based UDA-GR method. Specifically, we investigate the characteristic of gaits in the indoor and outdoor scenes, for estimating the gait sample uncertainty, which is used in the unsupervised fine-tuning on the target domain to alleviate the noises of the pseudo labels. We also establish a new benchmark for the proposed problem, experimental results on which show the effectiveness of the proposed method. We will release the benchmark and source code in this work to the public.
