Conditional Variational Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2023
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918402232156160 |
|---|---|
| author | della Maggiora, Gabriel Croquevielle, Luis Alberto Deshpande, Nikita Horsley, Harry Heinis, Thomas Yakimovich, Artur |
| author_facet | della Maggiora, Gabriel Croquevielle, Luis Alberto Deshpande, Nikita Horsley, Harry Heinis, Thomas Yakimovich, Artur |
| contents | Inverse problems aim to determine parameters from observations, a crucial task in engineering and science. Lately, generative models, especially diffusion models, have gained popularity in this area for their ability to produce realistic solutions and their good mathematical properties. Despite their success, an important drawback of diffusion models is their sensitivity to the choice of variance schedule, which controls the dynamics of the diffusion process. Fine-tuning this schedule for specific applications is crucial but time-costly and does not guarantee an optimal result. We propose a novel approach for learning the schedule as part of the training process. Our method supports probabilistic conditioning on data, provides high-quality solutions, and is flexible, proving able to adapt to different applications with minimum overhead. This approach is tested in two unrelated inverse problems: super-resolution microscopy and quantitative phase imaging, yielding comparable or superior results to previous methods and fine-tuned diffusion models. We conclude that fine-tuning the schedule by experimentation should be avoided because it can be learned during training in a stable way that yields better results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_02246 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Conditional Variational Diffusion Models della Maggiora, Gabriel Croquevielle, Luis Alberto Deshpande, Nikita Horsley, Harry Heinis, Thomas Yakimovich, Artur Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.2.6 Inverse problems aim to determine parameters from observations, a crucial task in engineering and science. Lately, generative models, especially diffusion models, have gained popularity in this area for their ability to produce realistic solutions and their good mathematical properties. Despite their success, an important drawback of diffusion models is their sensitivity to the choice of variance schedule, which controls the dynamics of the diffusion process. Fine-tuning this schedule for specific applications is crucial but time-costly and does not guarantee an optimal result. We propose a novel approach for learning the schedule as part of the training process. Our method supports probabilistic conditioning on data, provides high-quality solutions, and is flexible, proving able to adapt to different applications with minimum overhead. This approach is tested in two unrelated inverse problems: super-resolution microscopy and quantitative phase imaging, yielding comparable or superior results to previous methods and fine-tuned diffusion models. We conclude that fine-tuning the schedule by experimentation should be avoided because it can be learned during training in a stable way that yields better results. |
| title | Conditional Variational Diffusion Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning I.2.6 |
| url | https://arxiv.org/abs/2312.02246 |