mlsanityData to 14 Oct 2026

Flow Stochastic Segmentation Networks

arXiv 2507.18838 ↗First posted 24 Jul 2025cs.CV cs.AI stat.MLcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 73 of its 101 references that are in the map. First posted on arXiv 24 Jul 2025.

Builds on

73 of 101 references.

References · 73

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  6. 2023Segment Anythingcited by 8,234
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  8. 2022Flow Matching for Generative Modelingcited by 5,702
  9. 2018Neural Ordinary Differential Equationscited by 3,779
  10. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  11. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  12. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
38 more
  1. 2015Variational Inference with Normalizing Flowscited by 2,170
  2. 2016Density estimation using Real NVPcited by 2,042
  3. 2021TransUNet: Transformers Make Strong Encoders for Medical Image Segmentationcited by 1,558
  4. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,545
  5. 2017Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semanticscited by 1,358
  6. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  7. 2014NICE: Non-linear Independent Components Estimationcited by 1,058
  8. 2022Building Normalizing Flows with Stochastic Interpolantscited by 995
  9. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  10. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  11. 2016Pixel Recurrent Neural Networkscited by 816
  12. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 732
  13. 2017Masked Autoregressive Flow for Density Estimationcited by 684
  14. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  15. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  16. 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
  17. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 417
  18. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 307
  19. 2018A Probabilistic U-Net for Segmentation of Ambiguous Imagescited by 283
  20. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 280
  21. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 215
  22. 2015Conditional Random Fields as Recurrent Neural Networkscited by 214
  23. 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
  24. 2022MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Modelcited by 180
  25. 2017Breaking the Softmax Bottleneck: A High-Rank RNN Language Modelcited by 152
  26. 2019From Variational to Deterministic Autoencoderscited by 133
  27. 2019PHiSeg: Capturing Uncertainty in Medical Image Segmentationcited by 128
  28. 2019Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapsecited by 121
  29. 2020Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertaintycited by 101
  30. 2024Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directionscited by 97
  31. 2023Ambiguous Medical Image Segmentation using Diffusion Modelscited by 92
  32. 2024Normalizing Flows are Capable Generative Modelscited by 91
  33. 2018Taming VAEscited by 85
  34. 2024Variational Flow Matching for Graph Generationcited by 83
  35. 2023Non-Denoising Forward-Time Diffusionscited by 77
  36. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  37. 2019A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguitiescited by 65
  38. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 62

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Deterministic Mode Proposals: An Efficient Alternative to Generative Sampling for Ambiguous Segmentationcited by 0
  2. 2026Neural Architecture Distributions: A New Paradigm for Stochastic Segmentationcited by 0
  3. 2026Latent-to-Latent Flow for Volumetric Stochastic Segmentationcited by 0