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 1802.09778cs.CV
收藏

具有鲁棒目标转移的混合监督目标检测

Mixed Supervised Object Detection with Robust Objectness Transfer

Chinese Academy of Sciences (CASIA)(中国科学院(CASIA));Center for Research on Intelligent Perception and Computing (CRIPAC)(智能感知与计算研究中心(CRIPAC));National Laboratory of Pattern Recognition (NLPR)(模式识别国家重点实验室(NLPR));Institute of Automation(自动化研究所);University of Chinese Academy of Sciences (UCAS)(中国科学院大学(UCAS));CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心);University of Dundee(邓迪大学);School of Science and Engineering(理工学院);Computing(计算机学院)

Yan Li, Junge Zhang, Kaiqi Huang, Jianguo Zhang

摘要:

在本文中,我们考虑的问题,利用现有的完全标记的类别,以提高弱监督检测(WSD)的新的对象类别,我们称之为混合监督检测(MSD)。与以往的MSD方法直接将预训练的对象检测器从现有类别转移到新类别不同,我们提出了一种更合理和鲁棒的MSD对象转移方法。在我们的框架中,我们首先学习领域不变的对象知识,从现有的完全标记的类别。知识是基于对现有类别和新类别之间的分布差异鲁棒的不变特征来建模的;因此,所得到的知识将很好地推广到新类别,并且可以帮助检测模型拒绝干扰物(例如,对象部分)在新类别的弱标记图像中。在学习到的对象性知识的指导下,我们利用多实例学习(MIL)来建模对象和干扰物的概念,并进一步提高在弱标记图像中拒绝干扰物的能力。我们强大的对象转移方法优于现有的MSD方法,并在具有挑战性的ILSVRC 2013检测数据集和PASCAL VOC数据集上取得了最先进的结果。

英文摘要:

In this paper, we consider the problem of leveraging existing fully labeled categories to improve the weakly supervised detection (WSD) of new object categories, which we refer to as mixed supervised detection (MSD). Different from previous MSD methods that directly transfer the pre-trained object detectors from existing categories to new categories, we propose a more reasonable and robust objectness transfer approach for MSD. In our framework, we first learn domain-invariant objectness knowledge from the existing fully labeled categories. The knowledge is modeled based on invariant features that are robust to the distribution discrepancy between the existing categories and new categories; therefore the resulting knowledge would generalize well to new categories and could assist detection models to reject distractors (e.g., object parts) in weakly labeled images of new categories. Under the guidance of learned objectness knowledge, we utilize multiple instance learning (MIL) to model the concepts of both objects and distractors and to further improve the ability of rejecting distractors in weakly labeled images. Our robust objectness transfer approach outperforms the existing MSD methods, and achieves state-of-the-art results on the challenging ILSVRC2013 detection dataset and the PASCAL VOC datasets.

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。

↑