Flow Stochastic Segmentation Networks
This work addresses segmentation challenges in medical imaging, offering a novel generative approach with improved efficiency and performance.
The paper tackles the problem of generative segmentation by introducing Flow Stochastic Segmentation Networks (Flow-SSN), which overcome limitations of previous methods in estimating high-rank pixel-wise covariances and achieve state-of-the-art results on medical imaging benchmarks.
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.