Pseudo Label Rectification via Co-Teaching and Decoupling for Multisource Domain Adaptation in Semantic Segmentation
Author:
Affiliation:
1. Department of Multimedia Engineering, Dongguk University, Seoul, South Korea
2. Department of Electronics and Electrical Engineering, Daegu University, Gyeongsan-si, South Korea
Funder
National Research Foundation of Korea (NRF) Grant funded by the Korean Government
Korea Institute of Police Technology (KIPoT) Grant funded by the Korea Government (KNPA)
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Subject
General Engineering,General Materials Science,General Computer Science,Electrical and Electronic Engineering
Link
http://xplorestaging.ieee.org/ielx7/6287639/9668973/09868789.pdf?arnumber=9868789
Reference56 articles.
1. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks
2. MLSL: Multi-Level Self-Supervised Learning for Domain Adaptation with Spatially Independent and Semantically Consistent Labeling
3. Uncertainty-aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation
4. Category anchor-guided unsupervised domain adaptation for semantic segmentation;zhang;Proc Adv Neural Inf Process Syst,2019
5. Multiple fusion adaptation: A strong framework for unsupervised semantic segmentation adaptation;zhang;arXiv 2112 00295,2021
Cited by 6 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Dual Dynamic Consistency Regularization for Semi-Supervised Domain Adaptation;IEEE Access;2024
2. Point2Lane: Polyline-Based Reconstruction With Principal Points for Lane Detection;IEEE Transactions on Intelligent Transportation Systems;2023-12
3. Exploring High-Correlation Source Domain Information for Multi-Source Domain Adaptation in Semantic Segmentation;Proceedings of the 31st ACM International Conference on Multimedia;2023-10-26
4. Adversarial representation teaching with perturbation-agnostic student-teacher structure for semi-supervised learning;Applied Intelligence;2023-08-29
5. Multiple Tasks-Based Multi-Source Domain Adaptation Using Divide-and-Conquer Strategy;IEEE Access;2023
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3