Model Selection with Nonlinear Embedding for Unsupervised Domain Adaptation
This work addresses domain shift issues in machine learning applications like image classification, but it appears incremental as it builds on existing domain adaptation methods with a new validation procedure.
The paper tackles the problem of adapting classifiers from a source to a target distribution in unsupervised domain adaptation by introducing the Nonlinear Embedding Transform (NET) for domain alignment and clustering, resulting in enhanced classification performance as tested on popular image datasets.
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.