An attention-based feature pyramid network for single-stage small object detection | |
Jiao, Lin1,2; Kang, Chenrui3; Dong, Shifeng2,4; Chen, Peng1; Li, Gaoqiang1; Wang, Rujing2,4 | |
刊名 | MULTIMEDIA TOOLS AND APPLICATIONS |
2022-11-18 | |
关键词 | Object detection Feature pyramid network Feature fusion Single-stage Small object |
ISSN号 | 1380-7501 |
DOI | 10.1007/s11042-022-14159-2 |
通讯作者 | Jiao, Lin(ljiao@ahu.edu.cn) |
英文摘要 | Recently, single-stage detection methods have made great progress, achieving comparable accuracy to two-stage detection methods. However, they have poor performance over small object detection. In this work, we improve the performance of the single-stage detector for detecting objects of small sizes. The proposed method makes two major novel contributions. The first is to devise an attention-based feature pyramid network (aFPN) by introducing a learnable fusion factor for controlling feature information that deep layers deliver to shallow layers. The design of a learnable fusion factor could adapt a feature pyramid network to small object detection. The second contribution is to propose a soft-weighted loss function, which reduces the false attention during network training. To be specify, we reweight the contribution of training samples to the network loss according to their distances with the boundaries of the ground-truth box, leading to fewer false-positive detections. To verify the performance of the proposed method, we conduct extensive experiments on different datasets by comparing including RetinaNet, ATSS, FCOS, FreeAnchor, et al. Experimental results show that our method can achieve 44.2% AP on MS COCO dataset, 23.0% AP on VisDrone dataset, which significantly gains improvements with nearly no computation overhead. |
WOS研究方向 | Computer Science ; Engineering |
语种 | 英语 |
出版者 | SPRINGER |
WOS记录号 | WOS:000885231500004 |
内容类型 | 期刊论文 |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/131612] |
专题 | 中国科学院合肥物质科学研究院 |
通讯作者 | Jiao, Lin |
作者单位 | 1.Anhui Univ, Sch Internet, Hefei 230039, Peoples R China 2.Chinese Acad Sci, Inst Intelligent Machines, Hefei Inst Phys Sci, Hefei 230031, Peoples R China 3.Southwest Univ Sci & Technol, Mianyang 621010, Sichuan, Peoples R China 4.Univ Sci & Technol China, Hefei 230031, Peoples R China |
推荐引用方式 GB/T 7714 | Jiao, Lin,Kang, Chenrui,Dong, Shifeng,et al. An attention-based feature pyramid network for single-stage small object detection[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2022. |
APA | Jiao, Lin,Kang, Chenrui,Dong, Shifeng,Chen, Peng,Li, Gaoqiang,&Wang, Rujing.(2022).An attention-based feature pyramid network for single-stage small object detection.MULTIMEDIA TOOLS AND APPLICATIONS. |
MLA | Jiao, Lin,et al."An attention-based feature pyramid network for single-stage small object detection".MULTIMEDIA TOOLS AND APPLICATIONS (2022). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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