Abstract
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 (DVD), a novel LDM-based framework for a more practical variant of source-free domain adaptation (SFDA): the source provider may share not only a pre-trained classifier but also an auxiliary latent diffusion module, trained once on the source data and never exposing raw source samples. DVD encodes each source feature's label information into its latent vicinity by fitting a Gaussian prior over its k-nearest neighbors and training the diffusion network to “drift” noisy samples back to label-consistent representations. During adaptation, we sample from each target feature's latent vicinity, apply the frozen diffusion module to generate source-like cues, and use a simple InfoNCE loss to align the target encoder to these cues, explicitly transferring decision boundaries without source access. Across standard SFDA benchmarks, DVD outperforms state-of-the-art methods. We further show that the same latent diffusion module enhances the source classifier's accuracy on in-domain data and boosts performance in supervised classification and domain generalization experiments. DVD thus reinterprets LDMs as practical, privacy-preserving bridges for explicit knowledge transfer, addressing a core challenge in source-free domain adaptation that prior methods have yet to solve. Code is available on our Github: https://github.com/JingWang18/DVD-SFDA.
| Original language | English |
|---|---|
| Title of host publication | 39th Conference on Neural Information Processing Systems, NeurIPS 2025 |
| Publisher | Neural information processing systems foundation |
| Pages | 162190-162221 |
| Number of pages | 32 |
| ISBN (Electronic) | 9798331338275 |
| State | Published - 2025 |
| Event | 39th Conference on Neural Information Processing Systems, NeurIPS 2025 - San Diego, United States Duration: 2 Dec 2025 → 7 Dec 2025 |
Publication series
| Name | Advances in Neural Information Processing Systems |
|---|---|
| Volume | 38 |
| ISSN (Print) | 1049-5258 |
Conference
| Conference | 39th Conference on Neural Information Processing Systems, NeurIPS 2025 |
|---|---|
| Country/Territory | United States |
| City | San Diego |
| Period | 2/12/25 → 7/12/25 |
Bibliographical note
Publisher Copyright:© 2025 Neural information processing systems foundation. All rights reserved.
Fingerprint
Dive into the research topics of 'Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver