CASIA OpenIR  > 智能感知与计算研究中心
Image Piece Learning for Weakly Supervised Semantic Segmentation
Yi Li1; Yanqing Guo1; Yueying Kao2,3; Ran He2,3,4
AbstractThe task of semantic segmentation is to infer a predefined category label for each pixel in the image. For most cases, image segmentation is established as a fully supervised task. These methods all built on the basis of having access to sufficient pixel-wise annotated samples for training. However, obtaining the satisfied ground truth is not only labor intensive but also time-consuming, which severely hinders the generality of these fully supervised methods. Instead of pixel-level ground truth, weakly supervised approaches learn their models from much less prior information, e.g., image-level annotation. In this paper, we propose a novel conditional random field (CRF) based framework for weakly supervised semantic segmentation. Enlightened by jigsaw puzzles, we start the approach with merging superpixels from an image into larger pieces by a newly designed strategy. Then pieces from all the training images are gathered and associated with appropriate semantic labels by CRF. Thus, the piece library is constructed, achieving remarkable universality and flexibility. In the case of testing, we compare the superpixels with image pieces in the library and assign them the labels that minimize the potential energy. In addition, the proposed framework is fit for domain adaption and obtains promising results, which is of great practical value. Extensive experimental results on PASCAL VOC 2007, MSRC-21, and VOC 2012 databases demonstrate that our framework outperforms or is comparable to state-of-the-art segmentation methods.
KeywordConditional Random Field (Crf) Image Semantic Segmentation Piece Learning Weakly Supervised
WOS HeadingsScience & Technology ; Technology
Indexed BySCI
Funding OrganizationNational Natural Science Foundation of China (NSFC)(61402079) ; Foundation for Innovative Research Groups of the NSFC(71421001) ; Open Project Program of the National Laboratory of Pattern Recognition ; Youth Innovation Promotion Association Chinese Academy of Sciences(2015190) ; State Key Development Program(2016YFB1001001)
WOS Research AreaAutomation & Control Systems ; Computer Science
WOS SubjectAutomation & Control Systems ; Computer Science, Cybernetics
WOS IDWOS:000398966700007
Citation statistics
Cited Times:6[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Affiliation1.Dalian Univ Technol, Fac Elect Informat & Elect Engn, Sch Informat & Commun Engn, Dalian 116024, Peoples R China
2.Chinese Acad Sci, Ctr Res Intelligent Percept & Comp, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Yi Li,Yanqing Guo,Yueying Kao,et al. Image Piece Learning for Weakly Supervised Semantic Segmentation[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2017,47(4):648-659.
APA Yi Li,Yanqing Guo,Yueying Kao,&Ran He.(2017).Image Piece Learning for Weakly Supervised Semantic Segmentation.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,47(4),648-659.
MLA Yi Li,et al."Image Piece Learning for Weakly Supervised Semantic Segmentation".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 47.4(2017):648-659.
Files in This Item: Download All
File Name/Size DocType Version Access License
201704_TSMCS.pdf(1522KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Yi Li]'s Articles
[Yanqing Guo]'s Articles
[Yueying Kao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Yi Li]'s Articles
[Yanqing Guo]'s Articles
[Yueying Kao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Yi Li]'s Articles
[Yanqing Guo]'s Articles
[Yueying Kao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 201704_TSMCS.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.