{"ID":2891105,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18838","arxiv_id":"2507.18838","title":"Flow Stochastic Segmentation Networks","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2507.18838","url_pdf":"https://arxiv.org/pdf/2507.18838v1","authors":"[\"Fabio De Sousa Ribeiro\",\"Omar Todd\",\"Charles Jones\",\"Avinash Kori\",\"Raghav Mehta\",\"Ben Glocker\"]","published":"2025-07-24T22:26:28Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"stat.ML\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":611847,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2891105,"paper_url":"https://arxiv.org/abs/2507.18838","paper_title":"Flow Stochastic Segmentation Networks","repo_url":"https://github.com/biomedia-mira/flow-ssn","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}