Knowledge Commons of Institute of Automation,CAS
PSNet: Perspective-sensitive convolutional network for object detection | |
Zhang, Xin1,2; Liu, Yicheng3; Huo, Chunlei1,2; Xu, Nuo1,2; Wang, Lingfeng1,4; Pan, Chunhong1,2 | |
发表期刊 | NEUROCOMPUTING |
ISSN | 0925-2312 |
2022-01-11 | |
卷号 | 468页码:384-395 |
摘要 | Multi-view object detection is challenging due to the influence of the different view-angles on intra-class similarity. The uniformed feature representation of traditional detectors couples the object's perspective attribute and semantic feature, and the variances of perspective will cause intra-class differences. In this paper, a robust perspective-sensitive network (PSNet) is proposed to overcome the above problem. The uniformed feature is replaced by the perspective-specific structural feature, which makes the network perspective sensitive. Its essence is to learn multiple perspective spaces. In each perspective space, the semantic feature is decoupled from the perspective attribute and is robust to perspective variances. Perspective-sensitive RoI pooling and loss function are proposed for perspective-sensitive learning. Experiments on Pascal3D + and SpaceNet MOVI show the effectiveness and superiority of the PSNet. (c) 2021 Elsevier B.V. All rights reserved. |
关键词 | Object detection Perspective-sensitive Structural neural network |
DOI | 10.1016/j.neucom.2021.10.068 |
关键词[WOS] | CHALLENGE |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[62071466] ; National Natural Science Foundation of China[62076242] ; National Natural Science Foundation of China[61976208] ; National Key Research and Development Program of China[2018AAA0100400] |
项目资助者 | National Natural Science Foundation of China ; National Key Research and Development Program of China |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Artificial Intelligence |
WOS记录号 | WOS:000719336800002 |
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/173211/46468 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Huo, Chunlei |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 3.Chinese Univ Hong Kong, Hong Kong 999077, Peoples R China 4.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhang, Xin,Liu, Yicheng,Huo, Chunlei,et al. PSNet: Perspective-sensitive convolutional network for object detection[J]. NEUROCOMPUTING,2022,468:384-395. |
APA | Zhang, Xin,Liu, Yicheng,Huo, Chunlei,Xu, Nuo,Wang, Lingfeng,&Pan, Chunhong.(2022).PSNet: Perspective-sensitive convolutional network for object detection.NEUROCOMPUTING,468,384-395. |
MLA | Zhang, Xin,et al."PSNet: Perspective-sensitive convolutional network for object detection".NEUROCOMPUTING 468(2022):384-395. |
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 | ||
PSNet__Perspective_S(8656KB) | 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