Adversarial Bi-Regressor Network for Domain Adaptive Regression

2022-09-20 · Haifeng Xia, Pu Perry Wang, Toshiaki Koike-Akino, Ye Wang, Philip Orlik, Zhengming Ding

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.

📄 PDF Abstract BibTeX arXiv:2209.09943

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation regression

Regressive Domain Adaptation for Unsupervised Keypoint Detection

2021-03-10 · CVPR 2021 1 · Junguang Jiang, Yifei Ji, Ximei Wang, Yufeng Liu 외

Domain adaptation (DA) aims at transferring knowledge from a labeled source domain to an unlabeled target domain. Though many DA theories and algorithms have been proposed, most of them are tailored into classification s…

Domain Adaptation Keypoint Detection

A Lightweight Domain Adaptive Absolute Pose Regressor Using Barlow Twins Objective

2022-11-20 · Praveen Kumar Rajendran, Quoc-Vinh Lai-Dang, Luiz Felipe Vecchietti, Dongsoo Har

Identifying the camera pose for a given image is a challenging problem with applications in robotics, autonomous vehicles, and augmented/virtual reality. Lately, learning-based methods have shown to be effective for abso…

Autonomous Vehicles Camera Pose Estimation Pose Estimation regression

Boosting Ridge Regression for High Dimensional Data Classification

2020-03-25 · Jakramate Bootkrajang

Ridge regression is a well established regression estimator which can conveniently be adapted for classification problems. One compelling reason is probably the fact that ridge regression emits a closed-form solution the…

Classification Form General Classification regression+1

Fast, smooth and adaptive regression in metric spaces

2009-12-01 · NeurIPS 2009 12 · Samory Kpotufe

It was recently shown that certain nonparametric regressors can escape the curse of dimensionality in the sense that their convergence rates adapt to the intrinsic dimension of data (\cite{BL:65, SK:77}). We prove some s…

regression

Pointwise Tracking the Optimal Regression Function

2012-12-01 · NeurIPS 2012 12 · Yair Wiener, Ran El-Yaniv

This paper examines the possibility of a `reject option' in the context of least squares regression. It is shown that using rejection it is theoretically possible to learn `selective' regressors that can $\epsilon$-point…