Domain-Guided Conditional Diffusion Model for Unsupervised Domain Adaptation

TL;DR

This paper introduces DACDM, a domain-guided conditional diffusion model that generates high-quality target domain samples to enhance unsupervised domain adaptation, especially under large domain shifts.

Contribution

The paper proposes a novel diffusion-based generative model guided by domain and class information to improve UDA performance with limited target data.

Findings

DACDM significantly improves UDA accuracy across benchmarks.

Generated samples effectively bridge domain gaps.

The method outperforms existing UDA techniques.

Abstract

Limited transferability hinders the performance of deep learning models when applied to new application scenarios. Recently, Unsupervised Domain Adaptation (UDA) has achieved significant progress in addressing this issue via learning domain-invariant features. However, the performance of existing UDA methods is constrained by the large domain shift and limited target domain data. To alleviate these issues, we propose DomAin-guided Conditional Diffusion Model (DACDM) to generate high-fidelity and diversity samples for the target domain. In the proposed DACDM, by introducing class information, the labels of generated samples can be controlled, and a domain classifier is further introduced in DACDM to guide the generated samples for the target domain. The generated samples help existing UDA methods transfer from the source domain to the target domain more easily, thus improving the transfer performance. Extensive experiments on various benchmarks demonstrate that DACDM brings a large improvement to the performance of existing UDA methods.