.png){kind=icon}
返回
Self-corrected unsupervised domain adaptation
.png){kind=icon}
PRE
AI
DOI：10.1007/s11704-021-1010-8.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), which aims to use knowledge from a label-rich source domain to help learn unlabeled target domain, has recently attracted much attention. UDA methods mainly concentrate on source classification and distribution alignment between domains to expect the correct target prediction. While in this paper, we attempt to learn the target prediction end to end directly, and develop a Self-corrected unsupervised domain adaptation (SCUDA) method with probabilistic label correction. SCUDA adopts a probabilistic label corrector to learn and correct the target labels directly. Specifically, besides model parameters, those target pseudo-labels are also updated in learning and corrected by the anchor-variable, which preserves the class candidates for samples. Experiments on real datasets show the competitiveness of SCUDA.
Keyword:
unsupervised domain adaptation
adversarial earning
deep neural network
pseudo-labels
label corrector
期刊
IF:
4.6
论文数:
1.6K
被引数:
2.8K
机构
引用论文
Learning from group supervision: the impact of supervision deficiency on multi-label learning小组监督学习: 监督缺失对多标签学习的影响
PREAI
分享收藏分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏
查看更多内容