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

doi:10.1109/TPAMI.2022.3203402

	Memory-Based Cross-Image Contexts for Weakly Supervised Semantic Segmentation
	Fan, Junsong1,2 ; Zhang, Zhaoxiang1,3
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
	2023-05-01
卷号	45 期号:5 页码:6006-6020
通讯作者	Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
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.
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
DOI	10.1109/TPAMI.2022.3203402
收录类别	SCI
语种	英语
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
项目资助者	Major Project for New Generation of AI ; National Natural Science Foundation of China ; InnoHK program
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000964792800042
出版者	IEEE COMPUTER SOC
引用统计	被引频次：3[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/53249
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.Chinese Acad Sci CASIA, Inst Automat, Ctr Res Intelligent Percept & Comp CRIPAC, Natl Lab Pattern Recognit NLPR, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci UCAS, Beijing 100190, Peoples R China
第一作者单位	模式识别国家重点实验室
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.