LGMLSep 25, 2019

Matching Embeddings for Domain Adaptation

arXiv:1909.11651v44 citations
Originality Incremental advance
AI Analysis

This addresses the problem of transferring knowledge from labeled source to low-labeled target domains for researchers in machine learning, but it is incremental as it builds on existing adversarial and variational methods.

The paper tackles domain adaptation by proposing Adversarial Variational Domain Adaptation (AVDA), a semi-supervised method that aligns source and target domains using Gaussian Mixture Model embeddings, and it outperforms previous methods in most tasks on a digits dataset with fewer labeled samples.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes