Guardado en:
| Autor principal: | |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2410.00731 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916421451120640 |
|---|---|
| author | Nair, Lakshmi |
| author_facet | Nair, Lakshmi |
| contents | Synthetic data generation is an important application of machine learning in the field of medical imaging. While existing approaches have successfully applied fine-tuned diffusion models for synthesizing medical images, we explore potential improvements to this pipeline through feature-aligned diffusion. Our approach aligns intermediate features of the diffusion model to the output features of an expert, and our preliminary findings show an improvement of 9% in generation accuracy and ~0.12 in SSIM diversity. Our approach is also synergistic with existing methods, and easily integrated into diffusion training pipelines for improvements. We make our code available at \url{https://github.com/lnairGT/Feature-Aligned-Diffusion}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_00731 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improved Generation of Synthetic Imaging Data Using Feature-Aligned Diffusion Nair, Lakshmi Computer Vision and Pattern Recognition Machine Learning Synthetic data generation is an important application of machine learning in the field of medical imaging. While existing approaches have successfully applied fine-tuned diffusion models for synthesizing medical images, we explore potential improvements to this pipeline through feature-aligned diffusion. Our approach aligns intermediate features of the diffusion model to the output features of an expert, and our preliminary findings show an improvement of 9% in generation accuracy and ~0.12 in SSIM diversity. Our approach is also synergistic with existing methods, and easily integrated into diffusion training pipelines for improvements. We make our code available at \url{https://github.com/lnairGT/Feature-Aligned-Diffusion}. |
| title | Improved Generation of Synthetic Imaging Data Using Feature-Aligned Diffusion |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2410.00731 |