Model Selection with Nonlinear Embedding for Unsupervised Domain Adaptation

TL;DR

This paper introduces the Nonlinear Embedding Transform (NET) for unsupervised domain adaptation, which aligns domains nonlinearly and clusters similar data points to improve classification accuracy.

Contribution

The paper proposes a novel nonlinear domain alignment method called NET and a validation procedure for parameter tuning in unsupervised domain adaptation.

Findings

NET outperforms existing methods on image datasets

The validation procedure effectively tunes model parameters

Enhanced clustering improves classification results

Abstract

Domain adaptation deals with adapting classifiers trained on data from a source distribution, to work effectively on data from a target distribution. In this paper, we introduce the Nonlinear Embedding Transform (NET) for unsupervised domain adaptation. The NET reduces cross-domain disparity through nonlinear domain alignment. It also embeds the domain-aligned data such that similar data points are clustered together. This results in enhanced classification. To determine the parameters in the NET model (and in other unsupervised domain adaptation models), we introduce a validation procedure by sampling source data points that are similar in distribution to the target data. We test the NET and the validation procedure using popular image datasets and compare the classification results across competitive procedures for unsupervised domain adaptation.