Source-Free Domain Adaptation with Diffusion-Guided Source Data Generation

2024-02-07 · Shivang Chopra, Suraj Kothawade, Houda Aynaou, Aman Chadha

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.

📄 PDF Abstract BibTeX arXiv:2402.04929

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation Source-Free Domain Adaptation Unsupervised Domain Adaptation

Methods 이 논문이 사용한 방법론

Mixup Mixup is a data augmentation technique that generates a weighted combination of random image pairs from the training data. Given two images and their ground truth labels:…

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation

2025-10-01 · Jing Wang, Wonho Bae, Jiahong Chen, Wenxu Wang 외 arxiv

Recent work on latent diffusion models (LDMs) has focused almost exclusively on generative tasks, leaving their potential for discriminative transfer largely unexplored. We introduce Discriminative Vicinity Diffusion (DV…

Source-Free Domain Adaptation Domain Generalization

Discriminator-Guided Adaptive Diffusion for Source-Free Test-Time Adaptation under Image Corruptions

2026-04-26 · Francesco Olivato, Cigdem Beyan, Vittorio Murino arxiv

In this work, we study Source-Free Unsupervised Domain Adaptation under corruption-induced domain shifts, where performance degradation is caused by natural image corruptions that go beyond additive noise, including blur…

Unsupervised Domain Adaptation Test-time Adaptation

AUGCO: Augmentation Consistency-guided Self-training for Source-free Domain Adaptive Semantic Segmentation

2021-07-21 · Viraj Prabhu, Shivam Khare, Deeksha Kartik, Judy Hoffman

Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints. We focus on source-free dom…

Domain Adaptation Segmentation Semantic Segmentation Source-Free Domain Adaptation

Uncertainty-Guided Mixup for Semi-Supervised Domain Adaptation without Source Data

2021-07-14 · Ning Ma, Jiajun Bu, Zhen Zhang, Sheng Zhou

Present domain adaptation methods usually perform explicit representation alignment by simultaneously accessing the source data and target data. However, the source data are not always available due to the privacy preser…

Domain Adaptation Privacy Preserving Semi-supervised Domain Adaptation Source-Free Domain Adaptation

Source-Free Domain Adaptive Semantic Segmentation of Remote Sensing Images with Diffusion-Guided Label Enrichment

2025-09-23 · Wenjie Liu, Hongmin Liu, Lixin Zhang, Bin Fan arxiv

Research on unsupervised domain adaptation (UDA) for semantic segmentation of remote sensing images has been extensively conducted. However, research on how to achieve domain adaptation in practical scenarios where sourc…

Unsupervised Domain Adaptation Source-Free Domain Adaptation Semantic Segmentation