Toward Practical Weakly Supervised Semantic Segmentation via Point-Level Supervision

doi:10.1007/s11263-023-01862-2

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

	Toward Practical Weakly Supervised Semantic Segmentation via Point-Level Supervision
	Fan, Junsong 1,2; Zhang, Zhaoxiang 1,2,3
刊名	INTERNATIONAL JOURNAL OF COMPUTER VISION
	2023-08-12
页码	20
关键词	Weakly supervised learning Semantic segmentation Deep learning
ISSN号	0920-5691
DOI	10.1007/s11263-023-01862-2
通讯作者	Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
英文摘要	Weakly supervised semantic segmentation (WSSS) aims to reduce the cost of collecting dense pixel-level annotations for segmentation models by adopting weak labels to train. Although WSSS methods have achieved great success, recent approaches mainly concern the image-level label-based WSSS, which is limited to object-centric datasets instead of more challenging practical datasets that contain many co-occurrent classes. In comparison, point-level labels could provide some spatial information to address the class co-occurrent confusion problem. Meanwhile, it only requires an additional click when recognizing the targets, which is of negligible annotation overhead. Thus, we choose to study utilizing point labels for the general-purpose WSSS. The main difficulty of utilizing point-level labels is bridging the gap between the sparse point-level labels and the dense pixel-level predictions. To alleviate this problem, we propose a superpixel augmented pseudo-mask generation strategy and a class-aware contrastive learning approach, which manages to recover reliable dense constraints and apply them both to the segmentation models' final prediction and the intermediate features. Diagnostic experiments on the challenging Pascal VOC, Cityscapes, and the ADE20k datasets demonstrate that our approach can efficiently and effectively compensate for the sparse point-level labels and achieve cutting-edge performance on the point-based segmentation problems.
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关键词	SALIENT OBJECT DETECTION
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:001046969200001
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/173211/53987]
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
推荐引用方式 GB/T 7714	Fan, Junsong,Zhang, Zhaoxiang. Toward Practical Weakly Supervised Semantic Segmentation via Point-Level Supervision[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION,2023:20.
APA	Fan, Junsong,&Zhang, Zhaoxiang.(2023).Toward Practical Weakly Supervised Semantic Segmentation via Point-Level Supervision.INTERNATIONAL JOURNAL OF COMPUTER VISION,20.
MLA	Fan, Junsong,et al."Toward Practical Weakly Supervised Semantic Segmentation via Point-Level Supervision".INTERNATIONAL JOURNAL OF COMPUTER VISION (2023):20.