Gradual Domain Adaptation via Normalizing Flows

TL;DR

This paper introduces a novel approach using normalizing flows to improve gradual domain adaptation, especially when intermediate domains are limited and large shifts exist, leading to better classification performance.

Contribution

It proposes a new method leveraging normalizing flows to address limitations in existing gradual domain adaptation techniques with large domain gaps.

Findings

Improves classification accuracy in limited intermediate domain scenarios

Effectively models distribution shifts using normalizing flows

Demonstrates superior performance on real-world datasets

Abstract

Standard domain adaptation methods do not work well when a large gap exists between the source and target domains. Gradual domain adaptation is one of the approaches used to address the problem. It involves leveraging the intermediate domain, which gradually shifts from the source domain to the target domain. In previous work, it is assumed that the number of intermediate domains is large and the distance between adjacent domains is small; hence, the gradual domain adaptation algorithm, involving self-training with unlabeled datasets, is applicable. In practice, however, gradual self-training will fail because the number of intermediate domains is limited and the distance between adjacent domains is large. We propose the use of normalizing flows to deal with this problem while maintaining the framework of unsupervised domain adaptation. The proposed method learns a transformation from the distribution of the target domain to the Gaussian mixture distribution via the source domain. We evaluate our proposed method by experiments using real-world datasets and confirm that it mitigates the above-explained problem and improves the classification performance.