Knowledge Commons of Institute of Automation,CAS
APLNet: Attention-enhanced progressive learning network | |
Zhang, Hui1; Kang, Danqing1; He, Haibo2; Wang, Fei-Yue1,3,4 | |
发表期刊 | NEUROCOMPUTING |
ISSN | 0925-2312 |
2020-01-02 | |
卷号 | 371期号:2020页码:166-176 |
摘要 | Single-stage detectors depend on a simple regression network to predict category scores and regress box offsets for a fixed set of default boxes directly. The regression network needs to have high generalization capability, so as to accurately model the relationship between various object shapes and default boxes. Instead of complicating the regression network to increase generalization capability, we iteratively refine the default boxes to model this relationship sequentially. In this paper, we propose an Attention-Enhanced Progressive Learning Network (APLNet), which employs multiple stages for progressive detection to improve performance of single-stage detectors. Specifically, a progressive learning module is proposed to iteratively update the feature representation space and gradually regress the default boxes, which are pushed closer to the target objects progressively. In addition, since low-level features have less semantic information about objects, we design an attention enhancement module to generate the attention map applied to inject more semantically meaningful information into the low-level features. This module is supervised by boxes-induced segmentation annotations, i.e., no extra segmentation annotations are required. The multi-task loss function is used to train the whole network in an end-to-end way. Extensive experiments on PASCAL VOC 2007, PASCAL VOC 2012 and MS COCO datasets demonstrate the effectiveness of the proposed APLNet. (C) 2019 Elsevier B.V. All rights reserved. |
关键词 | Object detection Progressive learning Attention enhancement |
DOI | 10.1016/j.neucom.2019.08.086 |
关键词[WOS] | OBJECT DETECTION |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Joint Foundation of Guangdong[U1811463] ; Joint Foundation of Guangdong[U1811463] |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000493950600015 |
出版者 | ELSEVIER |
七大方向——子方向分类 | 目标检测、跟踪与识别 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/28871 |
专题 | 多模态人工智能系统全国重点实验室_平行智能技术与系统团队 |
通讯作者 | He, Haibo |
作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China 2.Univ Rhode Isl, Dept Elect Comp & Biomed Engn, Kingston, RI 02881 USA 3.Qingdao Acad Intelligent Ind, Innovat Ctr Parallel Vis, Qingdao, Shandong, Peoples R China 4.Macau Univ Sci & Technol, Inst Syst Engn, Macau, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Zhang, Hui,Kang, Danqing,He, Haibo,et al. APLNet: Attention-enhanced progressive learning network[J]. NEUROCOMPUTING,2020,371(2020):166-176. |
APA | Zhang, Hui,Kang, Danqing,He, Haibo,&Wang, Fei-Yue.(2020).APLNet: Attention-enhanced progressive learning network.NEUROCOMPUTING,371(2020),166-176. |
MLA | Zhang, Hui,et al."APLNet: Attention-enhanced progressive learning network".NEUROCOMPUTING 371.2020(2020):166-176. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
APLNet_ Attention-en(3114KB) | 期刊论文 | 作者接受稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论