Domain Gap Estimation for Source Free Unsupervised Domain Adaptation with Many Classifiers

TL;DR

This paper introduces a novel source-free unsupervised domain adaptation method using multiple classifiers to estimate domain gap and improve adaptation without access to source data, achieving state-of-the-art results.

Contribution

It proposes a multi-classifier approach to better estimate domain gap and enhance source-free UDA performance by maximizing classifier disagreement and agreement during training.

Findings

Achieves state-of-the-art performance in source-free UDA.

Outperforms existing methods even without source data access.

Effectively estimates domain gap using multiple classifiers.

Abstract

In theory, the success of unsupervised domain adaptation (UDA) largely relies on domain gap estimation. However, for source free UDA, the source domain data can not be accessed during adaptation, which poses great challenge of measuring the domain gap. In this paper, we propose to use many classifiers to learn the source domain decision boundaries, which provides a tighter upper bound of the domain gap, even if both of the domain data can not be simultaneously accessed. The source model is trained to push away each pair of classifiers whilst ensuring the correctness of the decision boundaries. In this sense, our many classifiers model separates the source different categories as far as possible which induces the maximum disagreement of many classifiers in the target domain, thus the transferable source domain knowledge is maximized. For adaptation, the source model is adapted to maximize the agreement among pairs of the classifiers. Thus the target features are pushed away from the decision boundaries. Experiments on several datasets of UDA show that our approach achieves state of the art performance among source free UDA approaches and can even compete to source available UDA methods.