arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.04404cs.CV
收藏

端到端比较注意力网络用于人员再识别

End-to-End Comparative Attention Networks for Person Re-identification

Hefei University of Technology(合肥工业大学);National University of Singapore(新加坡国立大学);Artificial Intelligence Institute, Qihoo 360 Technology Company, Ltd.(奇虎360科技有限公司人工智能研究院)

Hao Liu, Jiashi Feng, Meibin Qi, Jianguo Jiang, Shuicheng Yan

摘要:

在视频监控中,不相交视角下的人物重新识别已被广泛应用,但仍是一个具有挑战性的问题。主要挑战之一在于缺乏空间和时间线索,这使得难以处理照明条件、视角、身体姿势和遮挡的大变化。近年来,基于深度学习的身份识别方法被提出并取得了显著的效果。然而,这些方法中的大多数在一个一瞥中从整个帧中提取有区别的特征,而不区分要识别的人的各个部分。为了处理大的外观方差,通过多次瞥见来详细检查多个高度区分的局部区域的人图像是至关重要的。在本文中,我们提出了一个新的软注意力模型,即,端到端的比较注意力网络(CAN),专门为人员重新识别任务量身定制。端到端的CAN学习在看了几眼人的图像并自适应地比较它们的外观后,选择性地关注成对的人的图像的一部分。CAN模型能够学习图像的哪些部分与识别人员相关,并自动整合来自不同部分的信息,以确定一对图像是否属于同一个人。换句话说,我们提出的CAN模型模拟人类的感知过程,以验证两个图像是否来自同一个人。在三个基准人员重新识别数据集(包括CUHK 01,CHUHK 03和Market-1501)上进行的广泛实验清楚地表明,我们提出的用于人员重新识别的端到端CAN显著优于既定的基线,并提供了新的最先进的性能。

英文摘要:

Person re-identification across disjoint camera views has been widely applied in video surveillance yet it is still a challenging problem. One of the major challenges lies in the lack of spatial and temporal cues, which makes it difficult to deal with large variations of lighting conditions, viewing angles, body poses and occlusions. Recently, several deep learning based person re-identification approaches have been proposed and achieved remarkable performance. However, most of those approaches extract discriminative features from the whole frame at one glimpse without differentiating various parts of the persons to identify. It is essentially important to examine multiple highly discriminative local regions of the person images in details through multiple glimpses for dealing with the large appearance variance. In this paper, we propose a new soft attention based model, i.e., the end to-end Comparative Attention Network (CAN), specifically tailored for the task of person re-identification. The end-to-end CAN learns to selectively focus on parts of pairs of person images after taking a few glimpses of them and adaptively comparing their appearance. The CAN model is able to learn which parts of images are relevant for discerning persons and automatically integrates information from different parts to determine whether a pair of images belongs to the same person. In other words, our proposed CAN model simulates the human perception process to verify whether two images are from the same person. Extensive experiments on three benchmark person re-identification datasets, including CUHK01, CHUHK03 and Market-1501, clearly demonstrate that our proposed end-to-end CAN for person re-identification outperforms well established baselines significantly and offer new state-of-the-art performance.

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。

↑