In this work we address the problem of transferring knowledge obtained from a vast annotated source domain to a low labeled target domain. We propose Adversarial Variational Domain Adaptation (AVDA), a semi-supervised domain adaptation method based on deep variational embedded representations. We use approximate inference and domain adversarial methods to map samples from source and target domains into an aligned class-dependent embedding defined as a Gaussian Mixture Model. AVDA works as a classifier and considers a generative model that helps this classification. We used digits dataset for experimentation. Our results show that on a semi-supervised few-shot scenario our model outperforms previous methods in most of the adaptation tasks, even using a fewer number of labeled samples per class on target domain.
@article{arxiv.1909.11651,
title = {Matching Embeddings for Domain Adaptation},
author = {Manuel Pérez-Carrasco and Guillermo Cabrera-Vives and Pavlos Protopapas and Nicolás Astorga and Marouan Belhaj},
journal= {arXiv preprint arXiv:1909.11651},
year = {2021}
}