REACT: Remainder Adaptive Compensation for Domain Adaptive Object Detection

doi:10.1109/TIP.2024.3409024

	REACT: Remainder Adaptive Compensation for Domain Adaptive Object Detection
	Li, Haochen 1,2; Zhang, Rui3 ; Yao, Hantao4 ; Zhang, Xin3 ; Hao, Yifan 3; Song, Xinkai 3; Li, Ling1,2
发表期刊	IEEE TRANSACTIONS ON IMAGE PROCESSING
ISSN	1057-7149
	2024
卷号	33 页码:3735-3748
通讯作者	Zhang, Rui(zhangrui@ict.ac.cn) ; Li, Ling(liling@iscas.ac.cn)
摘要	Domain adaptive object detection (DAOD) aims to infer a robust detector on the target domain with the labelled source datasets. Recent studies utilize a feature extractor shared on the source and target domains to capture the domain-invariant features and the task-relevant information with both feature-alignment constraint and source annotations. However, the feature extractor shared across domains discards partial task-relevant information of the target domain due to the domain gap and lack of target annotations, leading to compromised discrimination capabilities within target domain. To this end, we propose a novel REmainder Adaptive CompensaTion network (REACT) to adaptively compensate the extracted features with the remainder features for generating task-relevant features. The key insight is that the remainder features contain the discarded task-relevant information, so they can be adapted to compensate for the inadequate target features. Especially, REACT introduces an additional remainder branch to regain the remainder features, and then adaptively utilizes them to compensate for the discarded task-relevant information, improving discrimination on the target domain. Extensive experiments over multiple cross-domain adaptation tasks with three baselines demonstrate that our approach gains significant improvements and achieves superior performance compared with highly-optimized state-of-the-art methods.
关键词	Unsupervised domain adaptation domain adaptive object detection feature extraction prototypes
DOI	10.1109/TIP.2024.3409024
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China
项目资助者	National Key Research and Development Program of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001248109100003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58781
专题	多模态人工智能系统全国重点实验室_多媒体计算
通讯作者	Zhang, Rui; Li, Ling
作者单位	1.Chinese Acad Sci, Inst Software, Intelligent Software Res Ctr, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, State Key Lab Processors, Beijing 100190, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Li, Haochen,Zhang, Rui,Yao, Hantao,et al. REACT: Remainder Adaptive Compensation for Domain Adaptive Object Detection[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2024,33:3735-3748.
APA	Li, Haochen.,Zhang, Rui.,Yao, Hantao.,Zhang, Xin.,Hao, Yifan.,...&Li, Ling.(2024).REACT: Remainder Adaptive Compensation for Domain Adaptive Object Detection.IEEE TRANSACTIONS ON IMAGE PROCESSING,33,3735-3748.
MLA	Li, Haochen,et al."REACT: Remainder Adaptive Compensation for Domain Adaptive Object Detection".IEEE TRANSACTIONS ON IMAGE PROCESSING 33(2024):3735-3748.