Show simple item record

dc.contributor.authorLu, Zhiwu
dc.contributor.authorFu, Zhenyong
dc.contributor.authorXiang, Tao
dc.contributor.authorHan, Peng
dc.contributor.authorWang, Liwei
dc.contributor.authorGao, Xin
dc.date.accessioned2016-05-08T14:08:45Z
dc.date.available2016-05-08T14:08:45Z
dc.date.issued2016-04-08
dc.identifier.citationLearning from Weak and Noisy Labels for Semantic Segmentation 2016:1 IEEE Transactions on Pattern Analysis and Machine Intelligence
dc.identifier.issn0162-8828
dc.identifier.issn2160-9292
dc.identifier.doi10.1109/TPAMI.2016.2552172
dc.identifier.urihttp://hdl.handle.net/10754/608585
dc.description.abstractA weakly supervised semantic segmentation (WSSS) method aims to learn a segmentation model from weak (image-level) as opposed to strong (pixel-level) labels. By avoiding the tedious pixel-level annotation process, it can exploit the unlimited supply of user-tagged images from media-sharing sites such as Flickr for large scale applications. However, these ‘free’ tags/labels are often noisy and few existing works address the problem of learning with both weak and noisy labels. In this work, we cast the WSSS problem into a label noise reduction problem. Specifically, after segmenting each image into a set of superpixels, the weak and potentially noisy image-level labels are propagated to the superpixel level resulting in highly noisy labels; the key to semantic segmentation is thus to identify and correct the superpixel noisy labels. To this end, a novel L1-optimisation based sparse learning model is formulated to directly and explicitly detect noisy labels. To solve the L1-optimisation problem, we further develop an efficient learning algorithm by introducing an intermediate labelling variable. Extensive experiments on three benchmark datasets show that our method yields state-of-the-art results given noise-free labels, whilst significantly outperforming the existing methods when the weak labels are also noisy.
dc.description.sponsorshipThis work was partially supported by National Natural Science Foundation of China (61573363 and 61573026), 973 Program of China (2014CB340403 and 2015CB352502), the Fundamental Research Funds for the Central Universities and the Research Funds of Renmin University of China (15XNLQ01), IBM Global SUR Award Program, European Research Council FP7 Project SUNNY (313243), and the funding from KAUST.
dc.language.isoen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)
dc.relation.urlhttp://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=7450177
dc.rights(c) 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
dc.subjectSemantic segmentation
dc.subjectlabel noise reduction
dc.subjectsparse learning
dc.subjectweakly supervised learning
dc.titleLearning from Weak and Noisy Labels for Semantic Segmentation
dc.typeArticle
dc.contributor.departmentComputational Bioscience Research Center (CBRC)
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journalIEEE Transactions on Pattern Analysis and Machine Intelligence
dc.eprint.versionPost-print
dc.contributor.institutionBeijing Key Laboratory of Big Data Man- agement and Analysis Methods, School of Information, Renmin University of China, Beijing 100872, China
dc.contributor.institutionSchool of Electronic Engineering and Computer Science, Queen Mary University of London, Mile End Road, London E1 4NS, United Kingdom
dc.contributor.institutionSchool of Electronics Engineering and Computer Science, Peking University, Beijing 100871, China
dc.contributor.affiliationKing Abdullah University of Science and Technology (KAUST)
kaust.personGao, Xin
refterms.dateFOA2018-06-14T08:02:55Z


Files in this item

Thumbnail
Name:
07450177.pdf
Size:
597.2Kb
Format:
PDF
Description:
Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record