arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.09561cs.CV
收藏

基于跨领域情景学习的领域广义人物再识别

Domain Generalized Person Re-Identification via Cross-Domain Episodic Learning

National Taiwan University(台湾大学);ASUS Intelligent Cloud Services(华硕智能云服务)

Ci-Siang Lin, Yuan-Chia Cheng, Yu-Chiang Frank Wang

摘要:

针对在不同的摄像机视图中识别同一个人的图像,人重新识别(re-ID)一直是计算机视觉中活跃的研究课题之一。大多数现有的重新识别工作需要从感兴趣的场景中收集大量的标记图像数据。当待识别数据与源域训练数据不同时,已经提出了许多领域自适应方法。然而,在训练期间仍然需要收集标记或未标记的目标域数据。在本文中,我们解决了一个更具挑战性和实用性的设置,域广义(DG)的人重新ID。也就是说,虽然有一些标记的源域数据集,我们没有访问任何目标域训练数据。为了在不知道目标感兴趣域的情况下学习域不变特征,我们提出了一种情景学习方案,该方案提出了Meta学习策略来利用观察到的源域标记数据。学习的特征将表现出足够的域不变属性,同时不会过度拟合源域数据或ID标签。我们在四个基准数据集上的实验证实了我们的方法优于最先进的方法。

英文摘要:

Aiming at recognizing images of the same person across distinct camera views, person re-identification (re-ID) has been among active research topics in computer vision. Most existing re-ID works require collection of a large amount of labeled image data from the scenes of interest. When the data to be recognized are different from the source-domain training ones, a number of domain adaptation approaches have been proposed. Nevertheless, one still needs to collect labeled or unlabelled target-domain data during training. In this paper, we tackle an even more challenging and practical setting, domain generalized (DG) person re-ID. That is, while a number of labeled source-domain datasets are available, we do not have access to any target-domain training data. In order to learn domain-invariant features without knowing the target domain of interest, we present an episodic learning scheme which advances meta learning strategies to exploit the observed source-domain labeled data. The learned features would exhibit sufficient domain-invariant properties while not overfitting the source-domain data or ID labels. Our experiments on four benchmark datasets confirm the superiority of our method over the state-of-the-arts.

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。

↑