Unsupervised Domain Adaptation: A Multi-task Learning-based Method

TL;DR

This paper introduces a multi-task learning approach for unsupervised domain adaptation, jointly learning classifiers for source and target domains by leveraging domain geometry and divergence, with algorithms based on RLS and SVMs.

Contribution

It proposes a novel multi-task learning framework for unsupervised domain adaptation, including two algorithms using RLS and SVMs, outperforming existing methods.

Findings

Outperforms state-of-the-art domain adaptation methods

Effective on synthetic and real-world tasks

Utilizes domain geometry and divergence in learning process

Abstract

This paper presents a novel multi-task learning-based method for unsupervised domain adaptation. Specifically, the source and target domain classifiers are jointly learned by considering the geometry of target domain and the divergence between the source and target domains based on the concept of multi-task learning. Two novel algorithms are proposed upon the method using Regularized Least Squares and Support Vector Machines respectively. Experiments on both synthetic and real world cross domain recognition tasks have shown that the proposed methods outperform several state-of-the-art domain adaptation methods.