Memory-Based Cross-Image Contexts for Weakly Supervised Semantic Segmentation

doi:10.1109/TPAMI.2022.3203402

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Memory-Based Cross-Image Contexts for Weakly Supervised Semantic Segmentation
	Fan, Junsong 1,3; Zhang, Zhaoxiang 1,2
刊名	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
	2023-05-01
卷号	45 期号:5 页码:6006-6020
关键词	Image segmentation Semantics Training Heating systems Context modeling Task analysis Computational modeling Weakly-supervised learning semantic segmentation image relationship cross-image context
ISSN号	0162-8828
DOI	10.1109/TPAMI.2022.3203402
通讯作者	Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
英文摘要	Weakly supervised semantic segmentation (WSSS) trains segmentation models by only weak labels, aiming to save the burden of expensive pixel-level annotations. This paper tackles the WSSS problem of utilizing image-level labels as the weak supervision. Previous approaches address this problem by focusing on generating better pseudo-masks from weak labels to train the segmentation model. However, they generally only consider every single image and overlook the potential cross-image contexts. We emphasize that the cross-image contexts among a group of images can provide complementary information for each other to obtain better pseudo-masks. To effectively employ cross-image contexts, we develop an end-to-end cross-image context module containing a memory bank mechanism and a transformer-based cross-image attention module. The former extracts cross-image contexts online from the feature encodings of input images and stores them as the memory. The latter mines useful information from the memorized contexts to provide the original queries with additional information for better pseudo-mask generation. We conduct detailed experiments on the Pascal VOC 2012 and the COCO dataset to demonstrate the advantage of utilizing cross-image contexts. Besides, state-of-the-art performance is also achieved. Codes are available at https://github.com/js-fan/MCIC.git.
资助项目	Major Project for New Generation of AI[2018AAA0100400] ; National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[U21B2042] ; National Natural Science Foundation of China[62072457] ; National Natural Science Foundation of China[62006231] ; InnoHK program
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE COMPUTER SOC
WOS记录号	WOS:000964792800042
资助机构	Major Project for New Generation of AI ; National Natural Science Foundation of China ; InnoHK program
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53248]
专题	多模态人工智能系统全国重点实验室
通讯作者	Zhang, Zhaoxiang
作者单位	1.Chinese Acad Sci HKISI CAS, Hong Kong Inst Sci & Innovat, Ctr Artificial Intelligence & Robot, Hong Kong 999077, Peoples R China 2.Univ Chinese Acad Sci UCAS, Beijing 100190, Peoples R China 3.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Fan, Junsong,Zhang, Zhaoxiang. Memory-Based Cross-Image Contexts for Weakly Supervised Semantic Segmentation[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(5):6006-6020.
APA	Fan, Junsong,&Zhang, Zhaoxiang.(2023).Memory-Based Cross-Image Contexts for Weakly Supervised Semantic Segmentation.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(5),6006-6020.
MLA	Fan, Junsong,et al."Memory-Based Cross-Image Contexts for Weakly Supervised Semantic Segmentation".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.5(2023):6006-6020.