A Slimmer Network with Polymorphic and Group Attention Modules for More Efficient Object Detection in Aerial Images
文献类型：期刊论文
| 作者 | Guo, Wei1; Li, Weihong1; Li, Zhenghao2; Gong, Weiguo1; Cui, Jinkai1; Wang, Xinran1 |
| 刊名 | REMOTE SENSING
 |
| 出版日期 | 2020-11-01 |
| 卷号 | 12期号:22页码:30 |
| 关键词 | aerial images object detection channel pruning polymorphic module (PM) group attention module (GAM) |
| DOI | 10.3390/rs12223750 |
| 通讯作者 | Li, Weihong(weihongli@cqu.edu.cn) |
| 英文摘要 | Object detection is one of the core technologies in aerial image processing and analysis. Although existing aerial image object detection methods based on deep learning have made some progress, there are still some problems remained: (1) Most existing methods fail to simultaneously consider multi-scale and multi-shape object characteristics in aerial images, which may lead to some missing or false detections; (2) high precision detection generally requires a large and complex network structure, which usually makes it difficult to achieve the high detection efficiency and deploy the network on resource-constrained devices for practical applications. To solve these problems, we propose a slimmer network for more efficient object detection in aerial images. Firstly, we design a polymorphic module (PM) for simultaneously learning the multi-scale and multi-shape object features, so as to better detect the hugely different objects in aerial images. Then, we design a group attention module (GAM) for better utilizing the diversiform concatenation features in the network. By designing multiple detection headers with adaptive anchors and the above-mentioned two modules, we propose a one-stage network called PG-YOLO for realizing the higher detection accuracy. Based on the proposed network, we further propose a more efficient channel pruning method, which can slim the network parameters from 63.7 million (M) to 3.3M that decreases the parameter size by 94.8%, so it can significantly improve the detection efficiency for real-time detection. Finally, we execute the comparative experiments on three public aerial datasets, and the experimental results show that the proposed method outperforms the state-of-the-art methods. |
| 资助项目 | Municipal Science and Technology Project of CQMMC, China[2017030502] |
| WOS研究方向 | Remote Sensing |
| 语种 | 英语 |
| WOS记录号 | WOS:000594583900001 |
| 出版者 | MDPI |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/12354]  |
| 专题 | 中国科学院重庆绿色智能技术研究院 |
| 通讯作者 | Li, Weihong |
| 作者单位 | 1.Chongqing Univ, Coll Optoelect Engn, Minist Educ, Key Lab Optoelect Technol & Syst, Chongqing 400044, Peoples R China 2.Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing 400714, Peoples R China |
| 推荐引用方式 GB/T 7714 | Guo, Wei,Li, Weihong,Li, Zhenghao,et al. A Slimmer Network with Polymorphic and Group Attention Modules for More Efficient Object Detection in Aerial Images[J]. REMOTE SENSING,2020,12(22):30. |
| APA | Guo, Wei,Li, Weihong,Li, Zhenghao,Gong, Weiguo,Cui, Jinkai,&Wang, Xinran.(2020).A Slimmer Network with Polymorphic and Group Attention Modules for More Efficient Object Detection in Aerial Images.REMOTE SENSING,12(22),30. |
| MLA | Guo, Wei,et al."A Slimmer Network with Polymorphic and Group Attention Modules for More Efficient Object Detection in Aerial Images".REMOTE SENSING 12.22(2020):30. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
浏览0
下载0
收藏0
其他版本
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。