Pixels Under Pressure: Exploring Fine-Tuning Paradigms for Foundation Models in High-Resolution Medical Imaging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: TehraniNasab, Zahra, Kumar, Amar, Arbel, Tal
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918128209887232
author TehraniNasab, Zahra
Kumar, Amar
Arbel, Tal
author_facet TehraniNasab, Zahra
Kumar, Amar
Arbel, Tal
contents Advancements in diffusion-based foundation models have improved text-to-image generation, yet most efforts have been limited to low-resolution settings. As high-resolution image synthesis becomes increasingly essential for various applications, particularly in medical imaging domains, fine-tuning emerges as a crucial mechanism for adapting these powerful pre-trained models to task-specific requirements and data distributions. In this work, we present a systematic study, examining the impact of various fine-tuning techniques on image generation quality when scaling to high resolution 512x512 pixels. We benchmark a diverse set of fine-tuning methods, including full fine-tuning strategies and parameter-efficient fine-tuning (PEFT). We dissect how different fine-tuning methods influence key quality metrics, including Fréchet Inception Distance (FID), Vendi score, and prompt-image alignment. We also evaluate the utility of generated images in a downstream classification task under data-scarce conditions, demonstrating that specific fine-tuning strategies improve both generation fidelity and downstream performance when synthetic images are used for classifier training and evaluation on real images. Our code is accessible through the project website - https://tehraninasab.github.io/PixelUPressure/.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14931
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pixels Under Pressure: Exploring Fine-Tuning Paradigms for Foundation Models in High-Resolution Medical Imaging
TehraniNasab, Zahra
Kumar, Amar
Arbel, Tal
Image and Video Processing
Graphics
Advancements in diffusion-based foundation models have improved text-to-image generation, yet most efforts have been limited to low-resolution settings. As high-resolution image synthesis becomes increasingly essential for various applications, particularly in medical imaging domains, fine-tuning emerges as a crucial mechanism for adapting these powerful pre-trained models to task-specific requirements and data distributions. In this work, we present a systematic study, examining the impact of various fine-tuning techniques on image generation quality when scaling to high resolution 512x512 pixels. We benchmark a diverse set of fine-tuning methods, including full fine-tuning strategies and parameter-efficient fine-tuning (PEFT). We dissect how different fine-tuning methods influence key quality metrics, including Fréchet Inception Distance (FID), Vendi score, and prompt-image alignment. We also evaluate the utility of generated images in a downstream classification task under data-scarce conditions, demonstrating that specific fine-tuning strategies improve both generation fidelity and downstream performance when synthetic images are used for classifier training and evaluation on real images. Our code is accessible through the project website - https://tehraninasab.github.io/PixelUPressure/.
title Pixels Under Pressure: Exploring Fine-Tuning Paradigms for Foundation Models in High-Resolution Medical Imaging
topic Image and Video Processing
Graphics
url https://arxiv.org/abs/2508.14931