The official code implementation of Unsupervised multi-source domain adaptation with graph convolution network and multi-alignment in mixed latent space
You can find the paper at this website：https://link.springer.com/article/10.1007/s11760-022-02298-w#citeas
If you find the paper helpful, please cite our paper.
TY - JOUR
AU - Chen, Dong
AU - Zhu, Hongqing
AU - Yang, Suyi
AU - Dai, Yiwen
PY - 2022
DA - 2022/08/17
TI - Unsupervised multi-source domain adaptation with graph convolution network and multi-alignment in mixed latent space
JO - Signal, Image and Video Processing
AB - This paper proposes an unsupervised multi-source domain adaptation algorithm with graph convolution network and multi-alignment in mixed latent space, which leverages domain labels, data structure, and category labels in a unified network but improves domain-invariant semantic representation by several innovations. Specifically, a novel data structure alignment is proposed to exploit the inherent properties of different domains while using current domain alignment and classification result alignment. Through this design, category consistency can be considered in both latent space, and domain and structure discrepancy between different source domains and the target domain can be eliminated. Moreover, we also use category alignment based on both CNN and GCN features to optimize category decision boundary. Experiment results show that the proposed method brings sufficient improvement especially for adaptation tasks with large shift in data distribution.
SN - 1863-1711
UR - https://doi.org/10.1007/s11760-022-02298-w
DO - 10.1007/s11760-022-02298-w
ID - Chen2022
ER -