Robust Ensembling Network for Unsupervised Domain Adaptation

TL;DR

This paper introduces a Robust Ensembling Network (REN) for unsupervised domain adaptation that leverages a teacher-student framework with a dual-network adversarial loss and consistency constraints to improve transfer stability and accuracy.

Contribution

The paper proposes a novel REN framework combining a teacher-student model with dual-network adversarial loss and consistency constraints for improved UDA performance.

Findings

REN outperforms state-of-the-art UDA methods on multiple datasets.

The dual-network adversarial loss enhances discriminator robustness.

Consistency constraints improve student network accuracy.

Abstract

Recently, in order to address the unsupervised domain adaptation (UDA) problem, extensive studies have been proposed to achieve transferrable models. Among them, the most prevalent method is adversarial domain adaptation, which can shorten the distance between the source domain and the target domain. Although adversarial learning is very effective, it still leads to the instability of the network and the drawbacks of confusing category information. In this paper, we propose a Robust Ensembling Network (REN) for UDA, which applies a robust time ensembling teacher network to learn global information for domain transfer. Specifically, REN mainly includes a teacher network and a student network, which performs standard domain adaptation training and updates weights of the teacher network. In addition, we also propose a dual-network conditional adversarial loss to improve the ability of the discriminator. Finally, for the purpose of improving the basic ability of the student network, we utilize the consistency constraint to balance the error between the student network and the teacher network. Extensive experimental results on several UDA datasets have demonstrated the effectiveness of our model by comparing with other state-of-the-art UDA algorithms.