An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training

TL;DR

This paper introduces a dual-module adversarial training framework for unsupervised domain adaptation, enhancing the extraction of domain-invariant features and outperforming existing methods in various tasks.

Contribution

It presents a novel dual-module architecture with discrepancy loss and adversarial training to improve domain-invariant feature learning in unsupervised domain adaptation.

Findings

Outperforms state-of-the-art in most unsupervised domain adaptation tasks

Effective in learning more domain invariant features

Applicable to various models utilizing domain invariant features

Abstract

In this paper, we propose a dual-module network architecture that employs a domain discriminative feature module to encourage the domain invariant feature module to learn more domain invariant features. The proposed architecture can be applied to any model that utilizes domain invariant features for unsupervised domain adaptation to improve its ability to extract domain invariant features. We conduct experiments with the Domain-Adversarial Training of Neural Networks (DANN) model as a representative algorithm. In the training process, we supply the same input to the two modules and then extract their feature distribution and prediction results respectively. We propose a discrepancy loss to find the discrepancy of the prediction results and the feature distribution between the two modules. Through the adversarial training by maximizing the loss of their feature distribution and minimizing the discrepancy of their prediction results, the two modules are encouraged to learn more domain discriminative and domain invariant features respectively. Extensive comparative evaluations are conducted and the proposed approach outperforms the state-of-the-art in most unsupervised domain adaptation tasks.