arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.08675cs.CV
收藏

基于Wasserstein距离的领域自适应目标检测

Wasserstein Distance Based Domain Adaptation for Object Detection

University of Maryland College Park(马里兰大学帕克分校);Booz Allen Hamilton(博思艾伦汉密尔顿);CCDC Army Research Laboratory(CCDC陆军研究实验室)

Pengcheng Xu, Prudhvi Gurram, Gene Whipps, Rama Chellappa

摘要:

在本文中,我们提出了一个对抗性的无监督领域自适应框架的目标检测。先前的方法利用基于源和目标域分布之间的交叉熵的对抗训练来学习最小化域间隙的共享特征映射。在这里,我们最小化两个分布之间的Wasserstein距离,而不是交叉熵或Jensen-Shannon发散,以提高领域自适应在高维特征空间中的稳定性,这是目标检测任务所固有的。此外,我们删除了源域和目标域之间共享特征映射的精确一致性约束,使得目标特征映射可以独立优化,这在域间隙较大的情况下是必要的。我们的经验表明,所提出的框架可以减轻在不同的情况下域移位,并提供改进的目标域目标检测性能。

英文摘要:

In this paper, we present an adversarial unsupervised domain adaptation framework for object detection. Prior approaches utilize adversarial training based on cross entropy between the source and target domain distributions to learn a shared feature mapping that minimizes the domain gap. Here, we minimize the Wasserstein distance between the two distributions instead of cross entropy or Jensen-Shannon divergence to improve the stability of domain adaptation in high-dimensional feature spaces that are inherent to object detection task. Additionally, we remove the exact consistency constraint of the shared feature mapping between the source and target domains, so that the target feature mapping can be optimized independently, which is necessary in the case of significant domain gap. We empirically show that the proposed framework can mitigate domain shift in different scenarios, and provide improved target domain object detection 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。

↑