This paper introduces a novel approach to leverage the generalizability of Diffusion Models for Source-Free Domain Adaptation (DM-SFDA). Our proposed DMSFDA method involves fine-tuning a pre-trained text-to-image diffusion model to generate source domain images using features from the target images to guide the diffusion process. Specifically, the pre-trained diffusion model is fine-tuned to generate source samples that minimize entropy and maximize confidence for the pre-trained source model. We then use a diffusion model-based image mixup strategy to bridge the domain gap between the source and target domains. We validate our approach through comprehensive experiments across a range of datasets, including Office-31, Office-Home, and VisDA. The results demonstrate significant improvements in SFDA performance, highlighting the potential of diffusion models in generating contextually relevant, domain-specific images.
@article{arxiv.2402.04929,
title = {Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation},
author = {Shivang Chopra and Suraj Kothawade and Houda Aynaou and Aman Chadha},
journal= {arXiv preprint arXiv:2402.04929},
year = {2024}
}
Comments
arXiv admin note: substantial text overlap with arXiv:2310.01701