CASIA OpenIR  > 精密感知与控制研究中心  > 精密感知与控制
DLA: Dynamic Label Assignment for Accurate One-stage Object Detection
He, Jiang1,2; Junrui, Xiao1,2; Qingyi, Gu1
2022-06-06
Conference Name2022 11th International Conference on Software and Computer Applications
Conference Date2022-2
Conference PlaceMalaysia
Abstract

One-stage object detector has been the most widely used framework in modern object detection due to its excellent performance and high efficiency. Label assignment, which is designed to discriminate positive and negative samples in training process, is closely correlated to the detection performance of one-stage detectors. Previous works commonly utilize geometric prior such as anchor box or key point to determine positive samples. Despite its simplicity, the heuristic strategy is rigid and it might limit the upper bound of detection performance. By introducing extra semantic information, prediction-aware geometric score and sample re-weighting mechanism, we propose a novel strategy called Dynamic Label Assignment in this paper. To validate the effectiveness and generalization of our method, we conduct extensive experiments on the MS COCO dataset. Without bells and whistles, our best model with ResNeXt-101 as backbone achieves state-of-the-art 46.5 AP, surpassing other strong methods such as SAPD (45.4 AP), ATSS (45.6 AP), and GFL (46.0 AP) by a large marigin.

Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48642
Collection精密感知与控制研究中心_精密感知与控制
Corresponding AuthorQingyi, Gu
Affiliation1.Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
He, Jiang,Junrui, Xiao,Qingyi, Gu. DLA: Dynamic Label Assignment for Accurate One-stage Object Detection[C],2022.
Files in This Item:
File Name/Size DocType Version Access License
DLA.pdf(722KB)会议论文 开放获取CC BY-NC-SAView
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[He, Jiang]'s Articles
[Junrui, Xiao]'s Articles
[Qingyi, Gu]'s Articles
Baidu academic
Similar articles in Baidu academic
[He, Jiang]'s Articles
[Junrui, Xiao]'s Articles
[Qingyi, Gu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[He, Jiang]'s Articles
[Junrui, Xiao]'s Articles
[Qingyi, Gu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: DLA.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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