arrow
返回

Class-conditional domain adaptation for semantic segmentation

delete2024-10-01
delete0
delete
OA
AI
Y
Yue Wang
Y
Yuke Li
J
James H. Elder
W
Wu, Runmin
卢
卢湖川 (Huchuan Lu) *
DOI:10.1007/s41095-023-0362-4delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
Semantic segmentation is an important sub-task for many applications. However, pixel-level ground-truth labeling is costly, and there is a tendency to overfit to training data, thereby limiting the generalization ability. Unsupervised domain adaptation can potentially address these problems by allowing systems trained on labelled datasets from the source domain (including less expensive synthetic domain) to be adapted to a novel target domain. The conventional approach involves automatic extraction and alignment of the representations of source and target domains globally. One limitation of this approach is that it tends to neglect the differences between classes: representations of certain classes can be more easily extracted and aligned between the source and target domains than others, limiting the adaptation over all classes. Here, we address this problem by introducing a Class-Conditional Domain Adaptation (CCDA) method. This incorporates a class-conditional multi-scale discriminator and class-conditional losses for both segmentation and adaptation. Together, they measure the segmentation, shift the domain in a class-conditional manner, and equalize the loss over classes. Experimental results demonstrate that the performance of our CCDA method matches, and in some cases, surpasses that of state-of-the-art methods.
Keyword:
domain adaptation
generative adversarial networks
semantic segmentation
cityscapes

期刊

Computational Visual Media 封面图
Computational Visual Media
IF:
18.3
论文数:
315
被引数:
2.6K

机构

U
University of Hong Kong
学者数:
4.1W
论文数: 3.9W
被引数: 10.1W
Y
york university - canada
学者数:
8.3K
论文数: 9.0K
被引数: 10
D
Dalian University of Technology
学者数:
6.0W
论文数: 4.4W
被引数: 5.5W
W
wuhan university
学者数:
8.1W
论文数: 5.8W
被引数: 70
学者 查看更多机构
引用论文

引用论文

Determinants of quality of life in patients with fibromyalgia: A structural equation modeling approach纤维肌痛患者生活质量的决定因素: 结构方程建模方法
err2017-02-03
err0
errOAAI
errJeong-Won Lee; Kyung-Eun Lee; Dong-Jin Park; Seong-Ho Kim; Seong-Su Nah; Ji Hyun Lee; Seong-Kyu Kim; Yeon-Ah Lee; Seung-Jae Hong; Hyun-Sook Kim; Hye-Soon Lee; Hyoun Ah Kim; Chung-Il Joung; Sang-Hyon Kim; Shin-Seok Lee
err分享
err收藏
Gross primary production of Mediterranean watersheds: Using isotope mass balance approach to improve estimations
err2024-01-23
err0
errOAAI
errAlexandra Mattei; Frédéric Huneau; Emilie Garel; Sébastien Santoni; Thomas Leydier; Yuliya Vystavna
err分享
err收藏
err分享
err收藏
err分享
err收藏
学者 查看更多内容