Adversarial Bi-Regressor Network for Domain Adaptive Regression
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909260243271680 |
|---|---|
| author | Xia, Haifeng Wang, Pu Perry Koike-Akino, Toshiaki Wang, Ye Orlik, Philip Ding, Zhengming |
| author_facet | Xia, Haifeng Wang, Pu Perry Koike-Akino, Toshiaki Wang, Ye Orlik, Philip Ding, Zhengming |
| contents | Domain adaptation (DA) aims to transfer the knowledge of a well-labeled source domain to facilitate unlabeled target learning. When turning to specific tasks such as indoor (Wi-Fi) localization, it is essential to learn a cross-domain regressor to mitigate the domain shift. This paper proposes a novel method Adversarial Bi-Regressor Network (ABRNet) to seek more effective cross-domain regression model. Specifically, a discrepant bi-regressor architecture is developed to maximize the difference of bi-regressor to discover uncertain target instances far from the source distribution, and then an adversarial training mechanism is adopted between feature extractor and dual regressors to produce domain-invariant representations. To further bridge the large domain gap, a domain-specific augmentation module is designed to synthesize two source-similar and target-similar intermediate domains to gradually eliminate the original domain mismatch. The empirical studies on two cross-domain regressive benchmarks illustrate the power of our method on solving the domain adaptive regression (DAR) problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_09943 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Adversarial Bi-Regressor Network for Domain Adaptive Regression Xia, Haifeng Wang, Pu Perry Koike-Akino, Toshiaki Wang, Ye Orlik, Philip Ding, Zhengming Human-Computer Interaction Computer Vision and Pattern Recognition Domain adaptation (DA) aims to transfer the knowledge of a well-labeled source domain to facilitate unlabeled target learning. When turning to specific tasks such as indoor (Wi-Fi) localization, it is essential to learn a cross-domain regressor to mitigate the domain shift. This paper proposes a novel method Adversarial Bi-Regressor Network (ABRNet) to seek more effective cross-domain regression model. Specifically, a discrepant bi-regressor architecture is developed to maximize the difference of bi-regressor to discover uncertain target instances far from the source distribution, and then an adversarial training mechanism is adopted between feature extractor and dual regressors to produce domain-invariant representations. To further bridge the large domain gap, a domain-specific augmentation module is designed to synthesize two source-similar and target-similar intermediate domains to gradually eliminate the original domain mismatch. The empirical studies on two cross-domain regressive benchmarks illustrate the power of our method on solving the domain adaptive regression (DAR) problem. |
| title | Adversarial Bi-Regressor Network for Domain Adaptive Regression |
| topic | Human-Computer Interaction Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2209.09943 |