Adversarial Bi-Regressor Network for Domain Adaptive Regression

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.

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

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Domain Adaptation: Learning Bounds and Algorithms
• Maximum Classifier Discrepancy for Unsupervised Domain Adaptation
• Joint Distribution Optimal Transportation for Domain Adaptation
• Transferrable Prototypical Networks for Unsupervised Domain Adaptation
• Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation
• Towards Fair Knowledge Transfer for Imbalanced Domain Adaptation
• FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation
• Adversarial Robustness for Unsupervised Domain Adaptation