We introduce the Flow Stochastic Segmentation Network (Flow-SSN), a generative segmentation model family featuring discrete-time autoregressive and modern continuous-time flow variants. We prove fundamental limitations of the low-rank parameterisation of previous methods and show that Flow-SSNs can estimate arbitrarily high-rank pixel-wise covariances without assuming the rank or storing the distributional parameters. Flow-SSNs are also more efficient to sample from than standard diffusion-based segmentation models, thanks to most of the model capacity being allocated to learning the base distribution of the flow, constituting an expressive prior. We apply Flow-SSNs to challenging medical imaging benchmarks and achieve state-of-the-art results. Code available: https://github.com/biomedia-mira/flow-ssn.
@article{arxiv.2507.18838,
title = {Flow Stochastic Segmentation Networks},
author = {Fabio De Sousa Ribeiro and Omar Todd and Charles Jones and Avinash Kori and Raghav Mehta and Ben Glocker},
journal= {arXiv preprint arXiv:2507.18838},
year = {2025}
}