.png){kind=icon}
Return
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}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
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.
Keywords:
Subspace learning
Domain adaptation
Feature extraction
Image classification
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
2.0W
Citations:
3.2W
Organization
Cited Papers
Autologous graft-versus-host disease: harnessing anti-tumor immunity through impaired self-tolerance
PREAI
ShareSaveShareSaveA Cascaded R-CNN With Multiscale Attention and Imbalanced Samples for Traffic Sign Detection.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAIShareSaveRETRACTED: Single-Image Super-Resolution Algorithm Based on Structural Self-Similarity and Deformation Block Features (Retracted Article)IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSave
View more