Nonlinear Embedding Transform for Unsupervised Domain Adaptation
This addresses the problem of adapting classifiers across different data distributions for computer vision applications, but it appears incremental as it builds on existing domain adaptation techniques.
The paper tackles unsupervised domain adaptation by introducing the Nonlinear Embedding Transform (NET), which combines domain alignment and similarity-based embedding, and it outperforms existing methods on multiple vision datasets.
The problem of domain adaptation (DA) deals with adapting classifier models trained on one data distribution to different data distributions. In this paper, we introduce the Nonlinear Embedding Transform (NET) for unsupervised DA by combining domain alignment along with similarity-based embedding. We also introduce a validation procedure to estimate the model parameters for the NET algorithm using the source data. Comprehensive evaluations on multiple vision datasets demonstrate that the NET algorithm outperforms existing competitive procedures for unsupervised DA.