Name
Abstract | ||
|---|---|---|
In this paper, we focus the problem of unsupervised domain adaptation which transfers knowledge from a well-labeled source domain to an unlabeled target domain with distinctive distributions. Based on Gromov-Hausdorff's theory, we proposed two kinds of feature mappings in the model of joint distribution adaptation by embedding the original feature subspace to a common subspace. It can been seen as a part of feature embedding used for the models based feature alignment. Our experiments show that constructed mappings have the abilities to alleviate the feature discrepancy and mitigate the distribution shift between source domain and target domains. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ACCESS.2021.3123281 | IEEE ACCESS |
Keywords | DocType | Volume |
Measurement, Symmetric matrices, Loss measurement, Sparse matrices, Extraterrestrial measurements, Deep learning, Training, Domain adaptation, metric information matrix, maximum mean discrepancy, Toeplitz matrix, convolutional filter mask | Journal | 9 |
ISSN | Citations | PageRank |
2169-3536 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wenjuan Ren | 1 | 0 | 0.34 |
| Shie Zhou | 2 | 0 | 0.34 |
| Zhanpeng Yang | 3 | 0 | 0.34 |
| Quan Shi | 4 | 0 | 0.34 |
| Xian Sun | 5 | 0 | 8.45 |
| Luyi Yang | 6 | 0 | 0.34 |