.png){kind=icon}
返回
Asymmetric alignment joint consistent regularization for multi-source domain adaptation
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-020-09883-6.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Most existing methods of domain adaptation are proposed for single-source settings, where the source data come from a single domain. However, in practice, the available data generally come from multiple domains with different distributions. In this paper, we propose asymmetric alignment joint consistent regularization (AACR) for multi-source domain adaptation. As for asymmetric alignment, we propose to learn asymmetric projections, explicitly treating each domain differently to avoid the loss of shared information. Data from different domains are encoded into a common subspace by these asymmetric projections, where the encoded features are further aligned to promote knowledge transfer. Further, we propose consistent regularization to better learn shared information and filter out domain-specific information. We formulate the two parts into a unified framework, and derive its global optimal solution. Comprehensive experiments are conducted to evaluate AACR, and the results verify the effectiveness and robustness of our method.
Keyword:
Subspace learning
Domain adaptation
Feature extraction
Image classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3
论文数:
2.0W
被引数:
3.2W
机构
引用论文
Autologous graft-versus-host disease: harnessing anti-tumor immunity through impaired self-tolerance
PREAI
分享收藏A Cascaded R-CNN With Multiscale Attention and Imbalanced Samples for Traffic Sign Detection用于交通标志检测的具有多尺度注意力和不平衡样本的级联r-cnn.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏RETRACTED: Single-Image Super-Resolution Algorithm Based on Structural Self-Similarity and Deformation Block Features (Retracted Article)IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏
查看更多内容