SLMS-SSD: Improving the balance of semantic and spatial information in object detection
Wang, Kunfeng1; Wang, Yadong1; Zhang, Shuqin1; Tian, Yonglin2,3; Li, Dazi1
Source PublicationEXPERT SYSTEMS WITH APPLICATIONS
ISSN0957-4174
2022-11-15
Volume206Pages:10
Corresponding AuthorWang, Kunfeng(wangkf@buct.edu.cn)
AbstractWith the development of deep learning technology, the research on convolutional neural network-based object detection is becoming more and more mature. However, most methods are unsatisfactory in dealing with the issue of semantic and spatial information imbalance. In this article, we extend the single-shot multibox detector SSD and propose a self-learning multi-scale object detection network by balancing the semantic information and spatial information, named SLMS-SSD. We first construct a shallow feature enhancement module to enhance the representation of small objects by extracting richer context information. Second, in terms of feature connectivity, we design a multi-scale feature selection module for intermediate layer features with a combination of top-down and direct up-samplings. Finally, in terms of feature strength, we design a self-learning feature fusion module for measuring the feature importance. We validate our model on the PASCAL VOC and MS COCO datasets, and the results demonstrate that it can effectively improve the accuracy of object detection, especially the accuracy of small object detection.
KeywordObject detection Deep learning Multi-scale feature selection Self-learning feature fusion
DOI10.1016/j.eswa.2022.117682
Indexed BySCI
Language英语
Funding ProjectNational Key R&D Pro-gram of China[2020YFC2003900] ; National Natural Sci-ence Foundation of China[62076020] ; Fundamen-tal Research Funds for the Central Universities, China[buctrc201933]
Funding OrganizationNational Key R&D Pro-gram of China ; National Natural Sci-ence Foundation of China ; Fundamen-tal Research Funds for the Central Universities, China
WOS Research AreaComputer Science ; Engineering ; Operations Research & Management Science
WOS SubjectComputer Science, Artificial Intelligence ; Engineering, Electrical & Electronic ; Operations Research & Management Science
WOS IDWOS:000832966000001
PublisherPERGAMON-ELSEVIER SCIENCE LTD
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/49849
Collection复杂系统管理与控制国家重点实验室_平行智能技术与系统团队
Corresponding AuthorWang, Kunfeng
Affiliation1.Beijing Univ Chem Technol, Coll Informat Sci & Technol, Beijing 100029, Peoples R China
2.Univ Sci & Technol China, Dept Automat, Hefei 230027, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Wang, Kunfeng,Wang, Yadong,Zhang, Shuqin,et al. SLMS-SSD: Improving the balance of semantic and spatial information in object detection[J]. EXPERT SYSTEMS WITH APPLICATIONS,2022,206:10.
APA Wang, Kunfeng,Wang, Yadong,Zhang, Shuqin,Tian, Yonglin,&Li, Dazi.(2022).SLMS-SSD: Improving the balance of semantic and spatial information in object detection.EXPERT SYSTEMS WITH APPLICATIONS,206,10.
MLA Wang, Kunfeng,et al."SLMS-SSD: Improving the balance of semantic and spatial information in object detection".EXPERT SYSTEMS WITH APPLICATIONS 206(2022):10.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Wang, Kunfeng]'s Articles
[Wang, Yadong]'s Articles
[Zhang, Shuqin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Wang, Kunfeng]'s Articles
[Wang, Yadong]'s Articles
[Zhang, Shuqin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Wang, Kunfeng]'s Articles
[Wang, Yadong]'s Articles
[Zhang, Shuqin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.