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
Learning pseudo labels for semi-and-weakly supervised semantic segmentation

文献类型：期刊论文

作者Wang, Yude2,3; Zhang, Jie2,3; Kan, Meina2,3; Shan, Shiguang1,2,3
刊名PATTERN RECOGNITION
出版日期2022-12-01
卷号132页码:10
关键词Semi -supervised Weakly supervised Semi -and -weakly supervised Semantic segmentation Pseudo label Self-training
ISSN号0031-3203
DOI10.1016/j.patcog.2022.108925
英文摘要In this paper, we aim to tackle semi-and-weakly supervised semantic segmentation (SWSSS), where many image-level classification labels and a few pixel-level annotations are available. We believe the most crucial point for solving SWSSS is to produce high-quality pseudo labels, and our method deals with it from two perspectives. Firstly, we introduce a class-aware cross entropy (CCE) loss for network training. Compared to conventional cross entropy loss, CCE loss encourages the model to distinguish concurrent classes only and simplifies the learning target of pseudo label generation. Secondly, we propose a progressive cross training (PCT) method to build cross supervision between two networks with a dynamic evaluation mechanism, which progressively introduces high-quality predictions as additional supervision for network training. Our method significantly improves the quality of generated pseudo labels in the regime with extremely limited annotations. Extensive experiments demonstrate that our approach outperforms state-of-the-art methods significantly. The code is released for public access 1 .(c) 2022 Elsevier Ltd. All rights reserved.
资助项目National Key R&D Program of China[2017YFA070 080 0] ; National Natural Science Founda- tion of China[62176251] ; National Natural Science Founda- tion of China[61976219] ; Beijing Nova Program[Z19110 0 0 01119123]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000874844700007
出版者ELSEVIER SCI LTD
源URL[http://119.78.100.204/handle/2XEOYT63/19754]  
专题中国科学院计算技术研究所期刊论文
通讯作者Zhang, Jie
作者单位1.Peng Cheng Natl Lab, Shenzhen 518055, Guangdong, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Key Lab Intelligent Informat Proc Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Yude,Zhang, Jie,Kan, Meina,et al. Learning pseudo labels for semi-and-weakly supervised semantic segmentation[J]. PATTERN RECOGNITION,2022,132:10.
APA Wang, Yude,Zhang, Jie,Kan, Meina,&Shan, Shiguang.(2022).Learning pseudo labels for semi-and-weakly supervised semantic segmentation.PATTERN RECOGNITION,132,10.
MLA Wang, Yude,et al."Learning pseudo labels for semi-and-weakly supervised semantic segmentation".PATTERN RECOGNITION 132(2022):10.

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。