Matching Embeddings for Domain Adaptation

2019/09/25 by Pérez-Carrasco, Manuel, Cabrera-Vives, Guillermo, Protopapas, Pavlos +2
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.1909.11651

Abstract

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.

Related

• Domain-Invariant Feature Alignment Using Variational Inference For Partial Domain Adaptation
• Active Adversarial Domain Adaptation
• Unsupervised Domain Adaptation Using Compact Internal Representations
• Improving Unsupervised Domain Adaptation with Variational Information Bottleneck
• Few-Shot Adversarial Domain Adaptation