热门
Focal and efficient IOU loss for accurate bounding box regression
文献类型：期刊论文
| 作者 | Zhang, Yi-Fan2,3,4 ; Ren, Weiqiang1; Zhang, Zhang2,3,4; Jia, Zhen3,4; Wang, Liang2,3,4; Tan, Tieniu2,3,4
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2022-09-28 |
| 卷号 | 506页码:146-157 |
| 关键词 | Object detection Loss function design Hard sample mining |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2022.07.042 |
| 通讯作者 | Zhang, Zhang(zzhang@nlpr.ia.ac.cn) |
| 英文摘要 | In object detection, bounding box regression (BBR) is a crucial step that determines the object localization performance. However, we find that most previous loss functions for BBR have two main drawbacks: (i) Both `n-norm and IOU-based loss functions are inefficient to depict the objective of BBR, which leads to slow convergence and inaccurate regression results. (ii) Most of the loss functions ignore the imbalance problem in BBR that the large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR. To mitigate the adverse effects caused thereby, we perform thorough studies to exploit the potential of BBR losses in this paper. Firstly, an Efficient Intersection over Union (EIOU) loss is proposed, which explicitly measures the discrepancies of three geometric factors in BBR, i.e., the overlap area, the central point and the side length. After that, we state the Effective Example Mining (EEM) problem and propose a regression version of focal loss to make the regression process focus on high-quality anchor boxes. Finally, the above two parts are combined to obtain a new loss function, namely Focal-EIOU loss. Extensive experiments on both synthetic and real datasets are performed. Notable superiorities on both the convergence speed and the localization accuracy can be achieved over other BBR losses. (c) 2022 Elsevier B.V. All rights reserved. |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000914170300012 |
| 出版者 | ELSEVIER |
| 源URL | [http://ir.ia.ac.cn/handle/173211/51383]  |
| 专题 | 自动化研究所_智能感知与计算研究中心 |
| 通讯作者 | Zhang, Zhang |
| 作者单位 | 1.Horizon Robot, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Chinese Acad Sci CASIA, Inst Automat, NLPR, Beijing, Peoples R China 4.Chinese Acad Sci CASIA, Inst Automat, CRIPAC, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Yi-Fan,Ren, Weiqiang,Zhang, Zhang,et al. Focal and efficient IOU loss for accurate bounding box regression[J]. NEUROCOMPUTING,2022,506:146-157. |
| APA | Zhang, Yi-Fan,Ren, Weiqiang,Zhang, Zhang,Jia, Zhen,Wang, Liang,&Tan, Tieniu.(2022).Focal and efficient IOU loss for accurate bounding box regression.NEUROCOMPUTING,506,146-157. |
| MLA | Zhang, Yi-Fan,et al."Focal and efficient IOU loss for accurate bounding box regression".NEUROCOMPUTING 506(2022):146-157. |
入库方式： OAI收割
来源：自动化研究所
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。