Domain Discrepancy Measure Using Complex Models in Unsupervised Domain Adaptation

01/30/2019
by   Jongyeong Lee, et al.
0

We address the problem of measuring the difference between two domains in unsupervised domain adaptation. We point out that the existing discrepancy measures are less informative when complex models such as deep neural networks are applied. Furthermore, estimation of the existing discrepancy measures can be computationally difficult and only limited to the binary classification task. To mitigate these shortcomings, we propose a novel discrepancy measure that is very simple to estimate for many tasks not limited to binary classification, theoretically-grounded, and can be applied effectively for complex models. We also provide easy-to-interpret generalization bounds that explain the effectiveness of a family of pseudo-labeling methods in unsupervised domain adaptation. Finally, we conduct experiments to validate the usefulness of our proposed discrepancy measure.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/11/2018

Unsupervised Domain Adaptation Based on Source-guided Discrepancy

Unsupervised domain adaptation is the problem setting where data generat...
research
12/26/2022

Application of Unsupervised Domain Adaptation for Structural MRI Analysis

The primary goal of this work is to study the effectiveness of an unsupe...
research
12/06/2017

Stretching Domain Adaptation: How far is too far?

While deep learning has led to significant advances in visual recognitio...
research
05/03/2022

Disentangled and Side-aware Unsupervised Domain Adaptation for Cross-dataset Subjective Tinnitus Diagnosis

EEG-based tinnitus classification is a valuable tool for tinnitus diagno...
research
03/09/2022

Unsupervised Domain Adaptation across FMCW Radar Configurations Using Margin Disparity Discrepancy

Commercial radar sensing is gaining relevance and machine learning algor...
research
03/15/2023

Practicality of generalization guarantees for unsupervised domain adaptation with neural networks

Understanding generalization is crucial to confidently engineer and depl...
research
06/26/2023

Pseudo-Trilateral Adversarial Training for Domain Adaptive Traversability Prediction

Traversability prediction is a fundamental perception capability for aut...

Please sign up or login with your details

Forgot password? Click here to reset