中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Global-and-Local Collaborative Learning for Co-Salient Object Detection

文献类型：期刊论文

作者Cong, Runmin3,4,5; Yang, Ning3,4; Li, Chongyi6; Fu, Huazhu7; Zhao, Yao3,4; Huang, Qingming8,9,10,11; Kwong, Sam1,2
刊名IEEE TRANSACTIONS ON CYBERNETICS
出版日期2022-07-22
页码12
ISSN号2168-2267
关键词Semantics Task analysis Feature extraction Convolution Object detection Computational modeling Collaborative work 3-D convolution co-salient object detection (CoSOD) global correspondence modeling (GCM) local correspondence modeling (LCM)
DOI10.1109/TCYB.2022.3169431
英文摘要The goal of co-salient object detection (CoSOD) is to discover salient objects that commonly appear in a query group containing two or more relevant images. Therefore, how to effectively extract interimage correspondence is crucial for the CoSOD task. In this article, we propose a global-and-local collaborative learning (GLNet) architecture, which includes a global correspondence modeling (GCM) and a local correspondence modeling (LCM) to capture the comprehensive interimage corresponding relationship among different images from the global and local perspectives. First, we treat different images as different time slices and use 3-D convolution to integrate all intrafeatures intuitively, which can more fully extract the global group semantics. Second, we design a pairwise correlation transformation (PCT) to explore similarity correspondence between pairwise images and combine the multiple local pairwise correspondences to generate the local interimage relationship. Third, the interimage relationships of the GCM and LCM are integrated through a global-and-local correspondence aggregation (GLA) module to explore more comprehensive interimage collaboration cues. Finally, the intra and inter features are adaptively integrated by an intra-and-inter weighting fusion (AEWF) module to learn co-saliency features and predict the co-saliency map. The proposed GLNet is evaluated on three prevailing CoSOD benchmark datasets, demonstrating that our model trained on a small dataset (about 3k images) still outperforms 11 state-of-the-art competitors trained on some large datasets (about 8k-200k images).
资助项目National Key Research and Development Program of China[2021ZD0112100] ; Beijing Nova Program[Z201100006820016] ; National Natural Science Foundation of China[62002014] ; National Natural Science Foundation of China[U1936212] ; National Natural Science Foundation of China[62120106009] ; National Natural Science Foundation of China[U21B2038] ; National Natural Science Foundation of China[61931008] ; Beijing Natural Science Foundation[4222013] ; Hong Kong Research Grants Council (RGC) General Research Funds[9042816 (CityU 11209819)] ; Hong Kong Research Grants Council (RGC) General Research Funds[9042958 (CityU 11203820)] ; Hong Kong Innovation and Technology Commission (InnoHK Project CIMDA) ; China Association for Science and Technology[2020QNRC001] ; Beijing Association for Science and Technology ; Hong Kong Scholars Program[XJ2020040] ; Fundamental Research Funds for the Central Universities[2021YJS046] ; CAAI-Huawei MindSpore Open Fund
WOS研究方向Automation & Control Systems ; Computer Science
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000833060900001
源URL[http://119.78.100.204/handle/2XEOYT63/19504]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Li, Chongyi
作者单位1.City Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China
2.City Univ Hong Kong Shenzhen Res Inst, Shenzhen 51800, Peoples R China
3.Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China
4.Beijing Jiaotong Univ, Beijing Key Lab Adv Informat Sci & Network Techno, Beijing 100044, Peoples R China
5.City Univ Hong Kong, Dept Comp Sci, Hong Kong, Peoples R China
6.Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore
7.ASTAR, Inst High Performance Comp, Singapore, Singapore
8.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 101408, Peoples R China
9.Univ Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing 101408, Peoples R China
10.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Cong, Runmin,Yang, Ning,Li, Chongyi,et al. Global-and-Local Collaborative Learning for Co-Salient Object Detection[J]. IEEE TRANSACTIONS ON CYBERNETICS,2022:12.
APA Cong, Runmin.,Yang, Ning.,Li, Chongyi.,Fu, Huazhu.,Zhao, Yao.,...&Kwong, Sam.(2022).Global-and-Local Collaborative Learning for Co-Salient Object Detection.IEEE TRANSACTIONS ON CYBERNETICS,12.
MLA Cong, Runmin,et al."Global-and-Local Collaborative Learning for Co-Salient Object Detection".IEEE TRANSACTIONS ON CYBERNETICS (2022):12.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。