期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 13, 期 6, 页码 2956-2964出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2017.2753319
关键词
Multiple instance learning (MIL); subspace model; weakly supervised learning
类别
资金
- National Science Foundation of China [61370213, 61771201, 61572158]
- National Key Technology Support Program of China [2014BAL05B06]
- Thousand Talents Plan of China
- Shenzhen Science and Technology Program [JCYJ20160330163900579, JCYJ20170413105929681]
Learning object detection models from weakly labeled data is an important topic in computer vision. Among various types of weak annotations, image-level object labeling is a natural one that tells the existence, but not the precise locations, of object instances in images. Learning object detectors from image-level labels can be naturally cast as a multiple instance learning (MIL) problem. Existing MIL approaches for object detection still suffer from high false positive rates due to the lack of advanced instances selection techniques. In this study, a subspace-based generative model is proposed to select positive instances by minimizing rank of the coefficient matrix associated with the subspace models. An incoherence term between the subspace model and some hard negative instances in then modeled by an epsilon-insensitive loss function. To further improve the discriminative ability, an ensemble strategy is proposed by employing multiple subspace models. Rigorous experiments are performed on several datasets, and the promising experimental results demonstrate that the proposed approach is superior to the state-of-the-art weakly supervised learning algorithms in terms of precision, recall, and F-score.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据