Abstract
Person re-identification (ReID) has made great strides thanks to the data-driven deep learning techniques. However, the existing benchmark datasets lack diversity, and models trained on these data cannot generalize well to dynamic wild scenarios. To meet the goal of improving the explicit generalization of ReID models, we develop a new Open-World, Diverse, Cross-Spatial-Temporal dataset named OWD with several distinct features. 1) Diverse collection scenes: multiple independent open-world and highly dynamic collecting scenes, including streets, intersections, shopping malls, etc. 2) Diverse lighting variations: long time spans from daytime to nighttime with abundant illumination changes. 3) Diverse person status: multiple camera networks in all seasons with normal/adverse weather conditions and diverse pedestrian appearances (e.g., clothes, personal belongings, poses, etc.). 4) Protected privacy: invisible faces for privacy critical applications. To improve the implicit generalization of ReID, we further propose a Latent Domain Expansion (LDE) method to develop the potential of source data, which decouples discriminative identity-relevant and trustworthy domain-relevant features and implicitly enforces domain-randomized identity feature space expansion with richer domain diversity to facilitate domain invariant representations. Our comprehensive evaluations with most benchmark datasets in the community are crucial for progress, although this work is far from the grand goal toward open-world and dynamic wild applications.
Abstract (translated)
由于数据驱动的深度学习技术的进步，人物识别（ReID）取得了很大进展。然而，现有的基准数据集缺乏多样性，因此在这些数据上训练的模型在动态野外场景下的泛化能力差。为了实现提高ReID模型的显式泛化目标，我们开发了一个名为OWD的新开放世界、多样、跨时空数据集，具有多个独特的特征。1) 多样化的场景收集：包括多个独立开放世界和高度动态的场景，如街道、交叉口、购物中心等。2) 多样化的光照变化：从白天到黑夜漫长的时间段，有丰富的光照变化。3) 多样的人的状态：所有季节的多个相机网络，包括正常/恶劣的天气条件以及多样的人行道外观（例如，衣服、个人物品、姿势等）。4) 保护隐私：对于关键隐私应用的可见面。为了提高ReID的隐式泛化，我们进一步提出了一个潜在领域扩展（LDE）方法，以开发数据源的潜在能力，该方法解耦了相关域的特征，隐含地强制域随机化身份特征空间扩张，并为领域不变的表示创造更丰富的领域多样性。我们在社区中的大多数基准数据集的全面评估对于进步来说至关重要，尽管这项工作离开放世界和动态野外应用的 grand goal 还有很长的路要走。
URL
https://arxiv.org/abs/2403.15119
