计算机与数字工程2023，Vol.51Issue(10)：2375-2378,4.DOI:10.3969/j.issn.1672-9722.2023.10.030
基于合成图像的语义分割任务域适应算法研究
Research on Domain Adaptation Algorithm for Semantic Segmentation Task Based on Synthetic Image
徐淑怡1
作者信息
- 1. 南京理工大学计算机科学与工程学院 南京 210018
- 折叠
摘要
Abstract
Deep domain adaptation is an extremely important topic in computer vision,and it is especially important to solve the domain adaptation problem in scenarios where it is very difficult and cumbersome to obtain manual labeled data,such as seman-tic segmentation tasks.Previous research has shown that even deep neural networks do not learn well the representation of informa-tion across domains.This paper focuses on adjusting the feature representations learned by the segmentation network in the source domain(synthetic image)and target domain(real image)under the semantic segmentation scenario.Different from previous meth-ods that use simple adversarial targets or superpixel information to assist,this paper proposes a generative adversarial network(GAN)-based method that brings feature representations in different domains closer in the learned feature space.Experimental re-sults show that the proposed method can achieve state-of-the-art results in a challenging scenario from the synthetic image domain to the real image domain.关键词
域适应/语义分割/生成对抗网络Key words
domain adaptation/semantic segmentation/GAN分类
信息技术与安全科学引用本文复制引用
徐淑怡..基于合成图像的语义分割任务域适应算法研究[J].计算机与数字工程,2023,51(10):2375-2378,4.
