Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation
This addresses domain adaptation without access to source data, which is incremental as it builds on existing diffusion model techniques.
The paper tackled source-free domain adaptation by fine-tuning a diffusion model to generate source domain images guided by target features, achieving significant performance improvements on datasets like Office-31, Office-Home, and VisDA.
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.