Similarity activation map for co-salient object detection

doi:10.1016/j.patrec.2022.10.009

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 脑机融合与认知评估

	Similarity activation map for co-salient object detection
	Wang, Yu1,2 ; Li, Shuxiao1,2
发表期刊	PATTERN RECOGNITION LETTERS
ISSN	0167-8655
	2022-11-01
卷号	163 页码:159-167
通讯作者	Li, Shuxiao(shuxiao.li@ia.ac.cn)
摘要	Co-salient object detection aims to detect the common objects within a group of relevant images, to which the spatial similarity contributes a lot. Existing methods utilize the inner product to compute the pixel-wise correlations, imitating the tracking methods. We present a novel yet effective module (Simi-larity Activation Module, SAM) to generate the similarity activation maps as the spatial modulator. The similarity activation maps are learned to highlight the common objects across the multiple images while suppressing other objects and the background. Moreover, we propose the Edge Extraction Module (EEM) and Feature Fusion Module (FFM) which can be easily applied to any existing methods without requiring architectural changes. Extensive experiments on different co-salient detection datasets demonstrate that our method (SimiNet) achieves state-of-the-art performance under various evaluation metrics.(c) 2022 Elsevier B.V. All rights reserved.
关键词	Co-salient object detection Similarity activation map Feature modulation Edge guidance
DOI	10.1016/j.patrec.2022.10.009
关键词[WOS]	DEEP
收录类别	SCI
语种	英语
资助项目	National Natural Science Foun-dation of China ; [62076020]
项目资助者	National Natural Science Foun-dation of China
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000877215000012
出版者	ELSEVIER
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/50551
专题	多模态人工智能系统全国重点实验室_脑机融合与认知评估
通讯作者	Li, Shuxiao
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wang, Yu,Li, Shuxiao. Similarity activation map for co-salient object detection[J]. PATTERN RECOGNITION LETTERS,2022,163:159-167.
APA	Wang, Yu,&Li, Shuxiao.(2022).Similarity activation map for co-salient object detection.PATTERN RECOGNITION LETTERS,163,159-167.
MLA	Wang, Yu,et al."Similarity activation map for co-salient object detection".PATTERN RECOGNITION LETTERS 163(2022):159-167.