CASIA OpenIR  > 精密感知与控制研究中心  > 精密感知与控制
Rethinking prediction alignment in one-stage object detection
Xiao, Junrui1,2; Jiang, He1,2; Li, Zhikai1,2; Gu, Qingyi1
Source PublicationNEUROCOMPUTING
ISSN0925-2312
2022-12-01
Volume514Pages:58-69
Corresponding AuthorGu, Qingyi(qingyi.gu@ia.ac.cn)
AbstractOwing to their excellent performance and efficiency, one-stage detectors have been widely used in mul-timedia tasks, such as temporal action detection, object tracking, and video detection. However, misalign-ment between classification and regression branches limits the accuracy of the detector. Most existing works add an auxiliary branch or adopt a specific sample assignment strategy to alleviate this problem, but with little effect. In this paper, we attribute this to incomplete branch interactions and propose a comprehensive Predictive Aligned Object Detector (PAOD), which can better correlate two subtasks. Specifically, our proposed PAOD achieves a better trade-off between prediction-interactive and prediction-specific by adopting an Iterative Aggregation Module (IAM) and a Mutual Constraint Module (MCM). We also design an aligned label assignment with an adaptive metric and re-weighting mechanism to further narrow the misalignment between prediction heads. With negligible additional overhead, PAOD achieves 50.4 AP at single-model single-scale testing on the MS-COCO branch, which demonstrates the effectiveness of our proposal. Notably, PAOD consistently outperforms previous sota such as ATSS (47.7 AP), BorderDet (48.0 AP) and GFL (48.2 AP) by a large margin on COCO test-dev data -set, and achieves better performance than various dense detectors on Pascal VOC and CrowdHuman data -sets. Code is available at https://github.com/JunruiXiao/PAOD.(c) 2022 Elsevier B.V. All rights reserved.
KeywordDeep learning Object detection Detection head Label assignment
DOI10.1016/j.neucom.2022.09.132
Indexed BySCI
Language英语
Funding ProjectScientific Instrument Developing Project of the Chinese Academy of Sciences ; [YJKYYQ20200045]
Funding OrganizationScientific Instrument Developing Project of the Chinese Academy of Sciences
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000869405900004
PublisherELSEVIER
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/50261
Collection精密感知与控制研究中心_精密感知与控制
Corresponding AuthorGu, Qingyi
Affiliation1.Chinese Acad Sci, Inst Automat, East Zhongguancun Rd, Beijing, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Jingjia Rd, Beijing, Peoples R China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Xiao, Junrui,Jiang, He,Li, Zhikai,et al. Rethinking prediction alignment in one-stage object detection[J]. NEUROCOMPUTING,2022,514:58-69.
APA Xiao, Junrui,Jiang, He,Li, Zhikai,&Gu, Qingyi.(2022).Rethinking prediction alignment in one-stage object detection.NEUROCOMPUTING,514,58-69.
MLA Xiao, Junrui,et al."Rethinking prediction alignment in one-stage object detection".NEUROCOMPUTING 514(2022):58-69.
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
[Xiao, Junrui]'s Articles
[Jiang, He]'s Articles
[Li, Zhikai]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiao, Junrui]'s Articles
[Jiang, He]'s Articles
[Li, Zhikai]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiao, Junrui]'s Articles
[Jiang, He]'s Articles
[Li, Zhikai]'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.