# Hybrid diffusion models: combining supervised and generative pretraining for label-efficient fine-tuning of segmentation models

arXiv: https://arxiv.org/abs/2408.03433 · HTML: https://mlsanity.com/paper/2408.03433/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 16 of its 50 references that are in the map.
- First posted on arXiv 6 Aug 2024.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 16 of 16)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [Variational Diffusion Models](https://mlsanity.com/paper/2107.00630/) (2021)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Progressive Distillation for Fast Sampling of Diffusion Models](https://mlsanity.com/paper/2202.00512/) (2022)
- [Diffusion Models Beat GANs on Image Classification](https://mlsanity.com/paper/2307.08702/) (2023)
- [XLSor: A Robust and Accurate Lung Segmentor on Chest X-Rays Using Criss-Cross Attention and Customized Radiorealistic Abnormalities Generation](https://mlsanity.com/paper/1904.09229/) (2019)
- [SupMAE: Supervised Masked Autoencoders Are Efficient Vision Learners](https://mlsanity.com/paper/2205.14540/) (2022)
- [Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense](https://mlsanity.com/paper/2302.01056/) (2023)
- [Robust semi-supervised segmentation with timestep ensembling diffusion models](https://mlsanity.com/paper/2311.07421/) (2023)
- [Label-efficient multi-organ segmentation with a diffusion model](https://mlsanity.com/paper/2402.15216/) (2024)

## Built on by (most cited first, 2 of 2)

- [DiffAtlas: GenAI-fying Atlas Segmentation via Image-Mask Diffusion](https://mlsanity.com/paper/2503.06748/) (2025)
- [GenMed: A Pairwise Generative Reformulation of Medical Diagnostic Tasks](https://mlsanity.com/paper/2605.10645/) (2026)

## Abstract (arXiv)

We are considering in this paper the task of label-efficient fine-tuning of segmentation models: We assume that a large labeled dataset is available and allows to train an accurate segmentation model in one domain, and that we have to adapt this model on a related domain where only a few samples are available. We observe that this adaptation can be done using two distinct methods: The first method, supervised pretraining, is simply to take the model trained on the first domain using classical supervised learning, and fine-tune it on the second domain with the available labeled samples. The second method is to perform self-supervised pretraining on the first domain using a generic pretext task in order to get high-quality representations which can then be used to train a model on the second domain in a label-efficient way. We propose in this paper to fuse these two approaches by introducing a new pretext task, which is to perform simultaneously image denoising and mask prediction on the first domain. We motivate this choice by showing that in the same way that an image denoiser conditioned on the noise level can be considered as a generative model for the unlabeled image distribution using the theory of diffusion models, a model trained using this new pretext task can be considered as a generative model for the joint distribution of images and segmentation masks under the assumption that the mapping from images to segmentation masks is deterministic. We then empirically show on several datasets that fine-tuning a model pretrained using this approach leads to better results than fine-tuning a similar model trained using either supervised or unsupervised pretraining only.