How does the Combined Risk Affect the Performance of Unsupervised Domain Adaptation Approaches?

TL;DR

This paper investigates how combined risk influences unsupervised domain adaptation performance and proposes E-MixNet, a method that uses enhanced mixup to control combined risk, improving existing UDA methods.

Contribution

The paper introduces E-MixNet, a novel approach employing enhanced mixup on source and pseudo-labeled target data to effectively control combined risk in UDA.

Findings

E-MixNet effectively curbs the increase of combined risk.

Adding the combined risk proxy improves performance of existing UDA methods.

Experimental results demonstrate the effectiveness of the proposed approach.

Abstract

Unsupervised domain adaptation (UDA) aims to train a target classifier with labeled samples from the source domain and unlabeled samples from the target domain. Classical UDA learning bounds show that target risk is upper bounded by three terms: source risk, distribution discrepancy, and combined risk. Based on the assumption that the combined risk is a small fixed value, methods based on this bound train a target classifier by only minimizing estimators of the source risk and the distribution discrepancy. However, the combined risk may increase when minimizing both estimators, which makes the target risk uncontrollable. Hence the target classifier cannot achieve ideal performance if we fail to control the combined risk. To control the combined risk, the key challenge takes root in the unavailability of the labeled samples in the target domain. To address this key challenge, we propose a method named E-MixNet. E-MixNet employs enhanced mixup, a generic vicinal distribution, on the labeled source samples and pseudo-labeled target samples to calculate a proxy of the combined risk. Experiments show that the proxy can effectively curb the increase of the combined risk when minimizing the source risk and distribution discrepancy. Furthermore, we show that if the proxy of the combined risk is added into loss functions of four representative UDA methods, their performance is also improved.