.png){kind=icon}
返回
Context-aware adaptive network for UDA semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1007/s00530-024-01397-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Unsupervised Domain Adaptation (UDA) plays a pivotal role in enhancing the segmentation performance of models in the target domain by mitigating the domain shift between the source and target domains. However, Existing UDA image mix methods often overlook the contextual association between classes, limiting the segmentation capability of the model. To address this issue, we propose the context-aware adaptive network that enhances the model's perception of contextual association information and maintains the contextual associations between different classes in mixed images, thereby improving the adaptability of the model. Firstly, we design a image mix strategy based on dynamic class correlation called DCCMix that constructs class correlation meta groups to preserve the contextual associations between different classes. Simultaneously, DCCMix dynamically adjusts the class proportion of the source domain within the mixed domain to gradually align with the distribution of the target domain, thereby improving training effectiveness. Secondly, the feature-wise fusion module and contextual feature-aware module are designed to better perceive contextual information of images and alleviate the issue of information loss during the feature extraction. Finally, we propose an adaptive class-edge weight to strengthen the segmentation ability of edge pixels in the model. Experimental results demonstrate that our proposed method achieves the mloU of 63.2% and 69.8% on two UDA benchmark tasks: SYNTHIA ->\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\rightarrow$$\end{document} Cityscapes and GTA ->\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\rightarrow$$\end{document} Cityscapes respectively. The code is available at https://github.com/yuheyuan/CAAN.
Keyword:
Semantic segmentation
Unsupervised domain adaptation(UDA)
Image mix
Contextual Information
期刊
IF:
3.1
论文数:
2.8K
被引数:
2.7K
机构
引用论文
The determinants of thinly capitalized tax avoidance structures: Evidence from Australian firms资本薄弱的避税结构的决定因素: 来自澳大利亚公司的证据
OAAI
OAAI分享收藏Inflexibility of mental planning: A characteristic disorder with prefrontal lobe lesions?心理计划的僵化: 前额叶病变的特征性障碍？
PREAI
分享收藏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.png)
PLOS ONEOAAI
PLOS ONEIF0
OAAI分享收藏Distant regulatory elements in a Sox10‐βGEO BAC transgene are required for expression of Sox10 in the enteric nervous system and other neural crest‐derived tissuesSox10-βgeo BAC转基因中的远距离调控元件是肠神经系统和其他神经源性组织中 Sox10 表达所必需的OAAI
OAAI分享收藏
查看更多内容