Return of Frustratingly Easy Domain Adaptation

11/17/2015
by   Baochen Sun, et al.
0

Unlike human learning, machine learning often fails to handle changes between training (source) and test (target) input distributions. Such domain shifts, common in practical scenarios, severely damage the performance of conventional machine learning methods. Supervised domain adaptation methods have been proposed for the case when the target data have labels, including some that perform very well despite being "frustratingly easy" to implement. However, in practice, the target domain is often unlabeled, requiring unsupervised adaptation. We propose a simple, effective, and efficient method for unsupervised domain adaptation called CORrelation ALignment (CORAL). CORAL minimizes domain shift by aligning the second-order statistics of source and target distributions, without requiring any target labels. Even though it is extraordinarily simple--it can be implemented in four lines of Matlab code--CORAL performs remarkably well in extensive evaluations on standard benchmark datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/06/2016

Deep CORAL: Correlation Alignment for Deep Domain Adaptation

Deep neural networks are able to learn powerful representations from lar...
research
12/06/2016

Correlation Alignment for Unsupervised Domain Adaptation

In this chapter, we present CORrelation ALignment (CORAL), a simple yet ...
research
09/29/2017

Unsupervised Domain Adaptation with Copula Models

We study the task of unsupervised domain adaptation, where no labeled da...
research
05/23/2017

Correlation Alignment by Riemannian Metric for Domain Adaptation

Domain adaptation techniques address the problem of reducing the sensiti...
research
04/23/2020

Supervised Domain Adaptation: Were we doing Graph Embedding all along?

The performance of machine learning models tends to suffer when the dist...
research
01/27/2020

A Primer on Domain Adaptation

Standard supervised machine learning assumes that the distribution of th...
research
11/28/2017

Minimal-Entropy Correlation Alignment for Unsupervised Deep Domain Adaptation

In this work, we face the problem of unsupervised domain adaptation with...

Please sign up or login with your details

Forgot password? Click here to reset