当前位置: X-MOL 学术Pattern Recogn. Lett. › 论文详情
Adversarial joint domain adaptation of asymmetric feature mapping based on least squares distance
Pattern Recognition Letters ( IF 3.255 ) Pub Date : 2020-06-09 , DOI: 10.1016/j.patrec.2020.06.007
Yumeng Yuan; Yuhua Li; Zhenlong Zhu; Ruixuan Li; Xiwu Gu

Joint domain adaptation aims to learn a high-quality classifier for an unlabeled dataset with the help of auxiliary data. Most methods reduce domain shifts through some carefully designed distance measures. Adversarial learning, which is rarely used for joint domain adaptation, can learn more transferable features while avoiding explicit distance measures. However, it usually suffers from a gradient vanishing problem during the training process. In order to solve the above problems, we propose a novel adversarial joint domain adaptation method, namely Asymmetric Feature mapping based on Least Squares Distance (AFLSD), which consists of asymmetric marginal distribution alignment and conditional distribution alignment. The asymmetric feature mapping, which can get closer features with more flexible parameters, is optimized by the least squares distance to reduce the gradient vanishing problem. The results of classification and other comparative experiments show that AFLSD is superior to the most advanced domain adaptation methods.
更新日期:2020-06-27

 

全部期刊列表>>
材料学研究精选
Springer Nature Live 产业与创新线上学术论坛
胸腔和胸部成像专题
自然科研论文编辑服务
ACS ES&T Engineering
ACS ES&T Water
屿渡论文,编辑服务
杨超勇
周一歌
华东师范大学
南京工业大学
清华大学
中科大
唐勇
跟Nature、Science文章学绘图
隐藏1h前已浏览文章
中洪博元
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
x-mol收录
福州大学
南京大学
王杰
左智伟
湖南大学
清华大学
吴杰
赵延川
中山大学化学工程与技术学院
试剂库存
天合科研
down
wechat
bug