Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting

doi:10.1109/TPAMI.2023.3301302

CASIA OpenIR > 模式识别实验室

	Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting
	Song, Chunfeng1 ; Ouyang, Wanli 2; Zhang, Zhaoxiang1,3
发表期刊	IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
ISSN	0162-8828
	2023-12-01
卷号	45 期号:12 页码:15996-16012
通讯作者	Zhang, Zhaoxiang(zhaoxiang.zhang@ia.ac.cn)
摘要	Semantic segmentation has achieved huge progress via adopting deep Fully Convolutional Networks (FCN). However, the performance of FCN-basedmodels severely rely on the amounts of pixel-level annotationswhich are expensive and time-consuming. Considering that bounding boxes also contain abundant semantic and objective information, an intuitive solution is to learn the segmentation with weak supervisions from the bounding boxes. Howto make full use of the class-level and region-level supervisions frombounding boxes to estimate the uncertain regions is the critical challenge for the weakly supervised learning task. In this paper, we propose a mixture model to address this problem. First, we introduce a box-driven class-wise maskingmodel (BCM) to remove irrelevant regions of each class. Moreover, based on the pixel-level segment proposal generated from the bounding box supervision, we calculate the mean filling rates of each class to serve as an important prior cue to guide the model ignoring the wrongly labeled pixels in proposals. To realize the more fine-grained supervision at instance-level, we further propose the anchor-based filling rate shifting module. Unlike previous methods that directly train models with the generated noisy proposals, our method can adjust the model learning dynamically with the adaptive segmentation loss. Thus it can help reduce the negative impacts from wrongly labeled proposals. Besides, based on the learned high-quality proposals with above pipeline, we explore to further boost the performance through two-stage learning. The proposed method is evaluated on the challenging PASCAL VOC 2012 benchmark and achieves 74.9% and 76.4% mean IoU accuracy under weakly and semi-supervised modes, respectively. Extensive experimental results show that the proposed method is effective and is on par with, or even better than current state-of-the-art methods.
关键词	Proposals Uncertainty Semantics Semantic segmentation Annotations Shape Adaptation models Box-driven masking filling rate uncertainty mining weakly supervised segmentation
DOI	10.1109/TPAMI.2023.3301302
收录类别	SCI
语种	英语
资助项目	National Key R & D Program of China[2022ZD0116500] ; Shanghai Committee of Science and Technology[21DZ1100100] ; National Natural Science Foundation of China[61836014] ; National Natural Science Foundation of China[U21B2042] ; National Natural Science Foundation of China[62006231] ; National Natural Science Foundation of China[62072457]
项目资助者	National Key R & D Program of China ; Shanghai Committee of Science and Technology ; National Natural Science Foundation of China
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:001130146400120
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/55497
专题	模式识别实验室
通讯作者	Zhang, Zhaoxiang
作者单位	1.Chinese Acad Sci CASIA, Ctr Res Intelligent Percept & Comp CRIPAC, State Key Lab Multimodal Artificial Intelligence, Natl Lab Pattern Recognit NLPR,Inst Automat, Beijing 100190, Peoples R China 2.Shanghai Artificial Intelligence Lab, Shanghai 201201, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol C, Beijing 100190, Peoples R China
第一作者单位	模式识别国家重点实验室
通讯作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Song, Chunfeng,Ouyang, Wanli,Zhang, Zhaoxiang. Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,2023,45(12):15996-16012.
APA	Song, Chunfeng,Ouyang, Wanli,&Zhang, Zhaoxiang.(2023).Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting.IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE,45(12),15996-16012.
MLA	Song, Chunfeng,et al."Weakly Supervised Semantic Segmentation via Box-Driven Masking and Filling Rate Shifting".IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 45.12(2023):15996-16012.