Semi-Supervised Domain Adaptation with Auto-Encoder via Simultaneous Learning

TL;DR

This paper introduces a semi-supervised domain adaptation framework using auto-encoders and simultaneous learning to improve distribution matching and classification transfer between source and target domains efficiently.

Contribution

It proposes a novel auto-encoder-based model with a simultaneous learning scheme and an improved MMD loss for stable domain adaptation.

Findings

Effective distribution matching between domains

High speed of adaptation with few iterations

Improved stability over state-of-the-art models

Abstract

We present a new semi-supervised domain adaptation framework that combines a novel auto-encoder-based domain adaptation model with a simultaneous learning scheme providing stable improvements over state-of-the-art domain adaptation models. Our framework holds strong distribution matching property by training both source and target auto-encoders using a novel simultaneous learning scheme on a single graph with an optimally modified MMD loss objective function. Additionally, we design a semi-supervised classification approach by transferring the aligned domain invariant feature spaces from source domain to the target domain. We evaluate on three datasets and show proof that our framework can effectively solve both fragile convergence (adversarial) and weak distribution matching problems between source and target feature space (discrepancy) with a high `speed' of adaptation requiring a very low number of iterations.