arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2209.02522cs.CV
收藏

UPAR:统一的行人属性识别和人物检索

UPAR: Unified Pedestrian Attribute Recognition and Person Retrieval

Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Fraunhofer IOSB(弗劳恩霍夫IOSB研究所);Fraunhofer Center for Machine Learning(弗劳恩霍夫机器学习中心)

Andreas Specker, Mickael Cormier, Jürgen Beyerer

摘要:

识别软生物特征行人属性在视频监控和时尚检索中至关重要。最近的工作在单个数据集上显示出有希望的结果。然而,这些方法在不同属性分布、视点、不同光照和低分辨率下的泛化能力仍然很少被理解,这是由于当前数据集中的强偏差和不同属性。为了缩小这一差距,并支持系统的调查,我们提出UPAR,统一的人属性识别数据集。它基于四个著名的个人属性识别数据集:PA 100 K,PETA,RAPv 2和Market 1501。我们通过提供330万个额外的注释来统一这些数据集,以协调数据集中12个属性类别中的40个重要的二进制属性。因此,我们使研究可推广的行人属性识别以及基于属性的人检索的第一次。由于图像分布、行人姿态、尺度和遮挡的巨大差异,现有方法在准确性和效率方面都受到很大挑战。此外,我们开发了一个强大的基线PAR和基于属性的人检索的正则化方法的深入分析的基础上。我们的模型在PA 100 k、PETA、RAPv 2、Market 1501-Attributes和UPAR的跨域和专业化设置中实现了最先进的性能。我们相信UPAR和我们强大的基线将为人工智能社区做出贡献,并促进对大规模、可推广的属性识别系统的研究。

英文摘要:

Recognizing soft-biometric pedestrian attributes is essential in video surveillance and fashion retrieval. Recent works show promising results on single datasets. Nevertheless, the generalization ability of these methods under different attribute distributions, viewpoints, varying illumination, and low resolutions remains rarely understood due to strong biases and varying attributes in current datasets. To close this gap and support a systematic investigation, we present UPAR, the Unified Person Attribute Recognition Dataset. It is based on four well-known person attribute recognition datasets: PA100K, PETA, RAPv2, and Market1501. We unify those datasets by providing 3,3M additional annotations to harmonize 40 important binary attributes over 12 attribute categories across the datasets. We thus enable research on generalizable pedestrian attribute recognition as well as attribute-based person retrieval for the first time. Due to the vast variance of the image distribution, pedestrian pose, scale, and occlusion, existing approaches are greatly challenged both in terms of accuracy and efficiency. Furthermore, we develop a strong baseline for PAR and attribute-based person retrieval based on a thorough analysis of regularization methods. Our models achieve state-of-the-art performance in cross-domain and specialization settings on PA100k, PETA, RAPv2, Market1501-Attributes, and UPAR. We believe UPAR and our strong baseline will contribute to the artificial intelligence community and promote research on large-scale, generalizable attribute recognition systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑