中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 智能感知与计算研究中心
Diag-IoU Loss for Object Detection

文献类型：期刊论文

作者Zhang, Shuangqing1,2,3; Li, Chenglong4,5; Jia, Zhen6; Liu, Lei7,8; Zhang, Zhang6; Wang, Liang6
刊名IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
出版日期2023-12-01
卷号33期号:12页码:7671-7683
关键词Object detection bounding box regression box diagonal IoU metric
ISSN号1051-8215
DOI10.1109/TCSVT.2023.3277621
通讯作者Li, Chenglong(lcl1314@foxmail.com) ; Jia, Zhen(zhen.jia@nlpr.ia.ac.cn)
英文摘要Existing IoU-based loss functions have achieved promising performance for bounding box regression in object detection. However, they cannot fully reflect the relation between the predicted and target boxes in the case of box inclusions, and might thus deteriorate detection accuracy and efficiency. In this paper, we design a novel similarity measurement based on the box diagonal called Diag-IoU to well represent the divergence between the predicted and target boxes even in the case of box inclusions, and thus achieve superior localization accuracy and fast convergence. In particular, we equivalently represent a rectangular box with its box diagonal, which contains exclusive and informative geometrical factors, and define the Diag-IoU based on the similarities of a set of sampled point pairs from the predicted and target box diagonals. Based on the Diag-IoU, we design a general Diag-IoU loss, which can provide holistic information in measuring two boxes and thus differentiate the two boxes in the case of box inclusions. To validate the effectiveness of the proposed method, we apply the Diag-IoU loss to several representative object detectors, including YOLO v5s, Faster R-CNN, and FCOS. Extensive experiments on the synthetic data and two challenging object detection benchmark datasets, i.e., MS COCO and PASCAL VOC, demonstrate the superior performance of the proposed Diag-IoU loss compared to previous IoU-based losses as well as other metrics.
WOS关键词REPRESENTATION ; NETWORK
资助项目Major Project for New Generation of Artificial Intelligence (AI)
WOS研究方向Engineering
语种英语
WOS记录号WOS:001121618300021
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Major Project for New Generation of Artificial Intelligence (AI)
源URL[http://ir.ia.ac.cn/handle/173211/57787]  
专题自动化研究所_智能感知与计算研究中心
通讯作者Li, Chenglong; Jia, Zhen
作者单位1.Anhui Univ, Sch Comp Sci & Technol, Key Lab Intelligent Comp & Signal Proc, Minist Educ, Hefei 230601, Peoples R China
2.Anhui Univ, Sch Comp Sci & Technol, Anhui Prov Key Lab Multimodal Cognit Computat, Hefei 230601, Peoples R China
3.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
4.Anhui Univ, Sch Artificial Intelligence, Informat Mat & Intelligent Sensing Lab Anhui Prov, Hefei 230601, Peoples R China
5.Anhui Univ, Sch Artificial Intelligence, Anhui Prov Key Lab Multimodal Cognit Computat, Hefei 230601, Peoples R China
6.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
7.Anhui Univ, Sch Comp Sci & Technol, Minist Educ, Key Lab Intelligent Comp & Signal Proc, Hefei 230601, Peoples R China
8.Anhui Univ, Sch Comp Sci & Technol, Anhui Prov KeyLaboratory Multimodal Cognit Computa, Hefei 230601, Peoples R China
推荐引用方式
GB/T 7714		 Zhang, Shuangqing,Li, Chenglong,Jia, Zhen,et al. Diag-IoU Loss for Object Detection[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2023,33(12):7671-7683.
APA Zhang, Shuangqing,Li, Chenglong,Jia, Zhen,Liu, Lei,Zhang, Zhang,&Wang, Liang.(2023).Diag-IoU Loss for Object Detection.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,33(12),7671-7683.
MLA Zhang, Shuangqing,et al."Diag-IoU Loss for Object Detection".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 33.12(2023):7671-7683.

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。