English

Adversarial Bi-Regressor Network for Domain Adaptive Regression

Human-Computer Interaction 2024-07-19 v2 Computer Vision and Pattern Recognition

Abstract

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.

Keywords

Cite

@article{arxiv.2209.09943,
  title  = {Adversarial Bi-Regressor Network for Domain Adaptive Regression},
  author = {Haifeng Xia and Pu Perry Wang and Toshiaki Koike-Akino and Ye Wang and Philip Orlik and Zhengming Ding},
  journal= {arXiv preprint arXiv:2209.09943},
  year   = {2024}
}

Comments

7 pages, 5 figures; IJCAI 2022; tested in the SPAWC2021 dataset for indoor localization

R2 v1 2026-06-28T01:46:01.411Z