Knowledge management system National Space Science Center,CAS
AGR-FCN: Adversarial Generated Region based on Fully Convolutional Networks for Single- and Multiple-Instance Object Detection | |
Alternative Title | WOS:000555473200008 |
Wang, Rui; Qin, Runnan1; Zou, Jialing; Zhang, Liang2 | |
Source Publication | 2019 IEEE INTERNATIONAL CONFERENCE ON IMAGING SYSTEMS & TECHNIQUES (IST 2019) |
2019 | |
Language | 英语 |
ISSN | 2471-6162 |
ISBN | 978-1-7281-3868-8 |
Abstract | Addressing the problem that object instance detection has poor detection effect on occluded objects in unstructured environment when using deep learning network, we explore the use of the strategy of adversarial learning in this paper. A three-step pipeline is carried to build a novel learning framework denoted as Adversarial Generated Region-based Fully Convolutional Networks (AGR-FCN). Our method first training the noted deep model Region-based Fully Convolutional Networks (R-FCN), and then an Adversarial Mask Dropout Network (AMDN), which can generate occlusion features for training samples, is designed based on the trained R-FCN. Through the training strategy of adversarial learning between network R-FCN and network AMDN, the ability of network R-FCN to learn the features of occluded objects as well as its instance-level object detection performance is improved. Numerical experiments are conducted for instance detection to compare our proposed AGR-FCN with the original R-FCN on the self-made BHGI Database and the public database GMU Kitchen Dataset, which demonstrate that our proposed AGR-FCN outperforms original R-FCN and can achieve an average detection accuracy of nearly 90%. |
Keyword | instance-level object detection adversarial learning Adversarial Mask Dropout Network Region-based Fully Convolutional Networks |
Conference Name | IEEE International Conference on Imaging Systems and Techniques (IST) . IEEE International School on Imaging |
Conference Date | DEC 08-10, 2019 |
Conference Place | Abu Dhabi, U ARAB EMIRATES |
Indexed By | CPCI |
Document Type | 会议论文 |
Identifier | http://ir.nssc.ac.cn/handle/122/7768 |
Collection | 中国科学院国家空间科学中心 |
Affiliation | 1.Univ Beiha, Key Lab Precis Opto Mechatron Technol, Minist Educ, Sch Instrumentat Sci & Opto Elect Engn, Beijing, Peoples R China 2.Chinese Acad Sci, Natl Space Sci Ctr, Beijing, Peoples R China 3.Univ Connecticut, Dept Elect & Comp Engn, 371 Fairfield Way,U-4157, Storrs, CT 06269 USA |
Recommended Citation GB/T 7714 | Wang, Rui,Qin, Runnan,Zou, Jialing,et al. AGR-FCN: Adversarial Generated Region based on Fully Convolutional Networks for Single- and Multiple-Instance Object Detection[C],2019. |
Files in This Item: | There are no files associated with this item. |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment