SIA OpenIR  > 机器人学研究室
Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation
Dong JH(董家华)1,2,3; Cong Y(丛杨)1,2; Sun G(孙干)1,2; Yang YS(杨云生)4; Xu XW(徐晓伟)5; Ding ZM(丁正明)6
Department机器人学研究室
Source PublicationIEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
ISSN1051-8215
2020
Pages1-14
Contribution Rank1
Funding OrganizationMinistry of Science and Technology of the Peoples Republic of China (2019YFB1310300) ; National Nature Science Foundation of China under Grant (61722311, U1613214, 61821005, 61533015) ; National Postdoctoral Innovative Talents Support Program (BX20200353)
KeywordWeakly-supervised learning endoscopic lesions segmentation semantic knowledge transfer domain adaptation
Abstract

Weakly-supervised learning has attracted growing research attention on medical lesions segmentation due to significant saving in pixel-level annotation cost. However, 1) most existing methods require effective prior and constraints to explore the intrinsic lesions characterization, which only generates incorrect and rough prediction; 2) they neglect the underlying semantic dependencies among weakly-labeled target enteroscopy diseases and fully-annotated source gastroscope lesions, while forcefully utilizing untransferable dependencies leads to the negative performance. To tackle above issues, we propose a new weakly-supervised lesions transfer framework, which can not only explore transferable domain-invariant knowledge across different datasets, but also prevent the negative transfer of untransferable representations. Specifically, a Wasserstein quantified transferability framework is developed to highlight widerange transferable contextual dependencies, while neglecting the irrelevant semantic characterizations. Moreover, a novel selfsupervised pseudo label generator is designed to equally provide confident pseudo pixel labels for both hard-to-transfer and easyto- transfer target samples. It inhibits the enormous deviation of false pseudo pixel labels under the self-supervision manner. Afterwards, dynamically-searched feature centroids are aligned to narrow category-wise distribution shift. Comprehensive theoretical analysis and experiments show the superiority of our model on the endoscopic dataset and several public datasets.

Language英语
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/27727
Collection机器人学研究室
Corresponding AuthorCong Y(丛杨)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110016, China
3.University of Chinese Academy of Sciences, Beijing 100049, China
4.Chinese PLA General Hospital, Beijing 100000, China
5.Department of Information Science, University of Arkansas at Little Rock, Arkansas 72204, USA
6.Department of Computer, Information and Technology, Indiana University-Purdue University Indianapolis, Indianapolis,IN 46202 USA
Recommended Citation
GB/T 7714
Dong JH,Cong Y,Sun G,et al. Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2020:1-14.
APA Dong JH,Cong Y,Sun G,Yang YS,Xu XW,&Ding ZM.(2020).Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,1-14.
MLA Dong JH,et al."Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2020):1-14.
Files in This Item:
File Name/Size DocType Version Access License
Weakly-Supervised Cr(4276KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Dong JH(董家华)]'s Articles
[Cong Y(丛杨)]'s Articles
[Sun G(孙干)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Dong JH(董家华)]'s Articles
[Cong Y(丛杨)]'s Articles
[Sun G(孙干)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Dong JH(董家华)]'s Articles
[Cong Y(丛杨)]'s Articles
[Sun G(孙干)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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