研究如何让大模型在高分辨率医学图像生成中更精准，提升真实场景下的应用效果。
Pixels Under Pressure: Exploring Fine-Tuning Paradigms for Foundation Models in High-Resolution Medical Imaging
- 对比全量与高效微调方法，探索高分辨图像生成的适配策略
- 512x512分辨率下，特定微调使生成图像质量提升，下游分类准确率提高12.3%
- 适合医学图像合成、数据稀缺场景下的模型优化研究者
基于扩散的通用模型在文本到图像生成方面取得进展，但多数研究局限于低分辨率。随着高分辨率图像合成在医学成像等领域的日益重要，微调成为适配预训练模型以满足特定任务和数据分布的关键机制。本文系统研究了不同微调技术在扩展至512x512高分辨率时对图像生成质量的影响。我们基准测试了多种微调方法，包括全量微调与参数高效微调（PEFT）。通过分析弗雷谢特初始距离（FID）、Vendi评分及提示-图像对齐度等关键指标，揭示不同方法对生成质量的影响。此外，在数据稀缺条件下评估生成图像在下游分类任务中的实用性，结果表明特定微调策略能同时提升生成保真度与分类器性能。代码已公开于项目主页：https://tehraninasab.github.io/PixelUPressure/
原文摘要 · Abstract (English)
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/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。