Robust Semi-Supervised Segmentation with Timestep Ensembling Diffusion Models

Abstract

Medical image segmentation is challenging due to limited data and annotations. Denoising diffusion probabilistic models (DDPM) show promise in modelling natural image distributions and are successfully applied in medical imaging. Our research focuses on semi-supervised image segmentation using diffusion models' latent representations and addressing domain generalisation. We found that optimal performance depends on the choice of diffusion steps and ensembling. Our model outperformed in domain-shifted settings while remaining competitive within domain, highlighting DDPMs' potential for medical image segmentation.

Cite

Text

Rosnati et al. "Robust Semi-Supervised Segmentation with Timestep Ensembling Diffusion Models." NeurIPS 2023 Workshops: DGM4H, 2023.

Markdown

[Rosnati et al. "Robust Semi-Supervised Segmentation with Timestep Ensembling Diffusion Models." NeurIPS 2023 Workshops: DGM4H, 2023.](https://mlanthology.org/neuripsw/2023/rosnati2023neuripsw-robust/)

BibTeX

@inproceedings{rosnati2023neuripsw-robust,
  title     = {{Robust Semi-Supervised Segmentation with Timestep Ensembling Diffusion Models}},
  author    = {Rosnati, Margherita and Roschewitz, Mélanie and Glocker, Ben},
  booktitle = {NeurIPS 2023 Workshops: DGM4H},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/rosnati2023neuripsw-robust/}
}