Rethinking prediction alignment in one-stage object detection

doi:10.1016/j.neucom.2022.09.132

	Rethinking prediction alignment in one-stage object detection
	Xiao, Junrui1,2 ; Jiang, He1,2 ; Li, Zhikai1,2 ; Gu, Qingyi1
Source Publication	NEUROCOMPUTING
ISSN	0925-2312
	2022-12-01
Volume	514 Pages:58-69
Corresponding Author	Gu, Qingyi(qingyi.gu@ia.ac.cn)
Abstract	Owing 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.
Keyword	Deep learning Object detection Detection head Label assignment
DOI	10.1016/j.neucom.2022.09.132
Indexed By	SCI
Language	英语
Funding Project	Scientific Instrument Developing Project of the Chinese Academy of Sciences ; [YJKYYQ20200045]
Funding Organization	Scientific Instrument Developing Project of the Chinese Academy of Sciences
WOS Research Area	Computer Science
WOS Subject	Computer Science, Artificial Intelligence
WOS ID	WOS:000869405900004
Publisher	ELSEVIER
Citation statistics
Document Type	期刊论文
Identifier	http://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 Author	Gu, Qingyi
Affiliation	1.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 Affilication	Institute of Automation, Chinese Academy of Sciences
Corresponding Author Affilication	Institute 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.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Institution:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh

精密感知与控制研究中心知识库