{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:19:14Z","timestamp":1777889954881,"version":"3.51.4"},"reference-count":99,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01369","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14754-14765","source":"Crossref","is-referenced-by-count":0,"title":["Flow Stochastic Segmentation Networks"],"prefix":"10.1109","author":[{"given":"Fabio","family":"De Sousa Ribeiro","sequence":"first","affiliation":[{"name":"Imperial College London,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Omar","family":"Todd","sequence":"additional","affiliation":[{"name":"Imperial College London,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles","family":"Jones","sequence":"additional","affiliation":[{"name":"Imperial College London,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Avinash","family":"Kori","sequence":"additional","affiliation":[{"name":"Imperial College London,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raghav","family":"Mehta","sequence":"additional","affiliation":[{"name":"Imperial College London,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ben","family":"Glocker","sequence":"additional","affiliation":[{"name":"Imperial College London,London,UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"265","article-title":"{TensorFlow}: a system for {Large-Scale} machine learning","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Abadi"},{"key":"ref2","article-title":"Building normalizing flows with stochastic interpolants","volume-title":"The Eleventh International Conference on Learning Representations (ICLR)","author":"Albergo"},{"key":"ref3","article-title":"Segdiff: Image segmentation with diffusion probabilistic models","author":"Amit","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1118\/1.3528204"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72114-4_14"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32245-8_14"},{"key":"ref7","article-title":"Failure detection in medical image classification: A reality check and benchmarking testbed","author":"Bernhardt","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02373-y"},{"key":"ref9","article-title":"Qubiq: Uncertainty quantification for biomedical image segmentation challenge","author":"Bran","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","article-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref12","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref13","volume-title":"torchdiffeq","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-78191-0_55"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04332-4"},{"key":"ref16","first-page":"6490","article-title":"Introducing routing uncertainty in capsule networks","volume":"33","author":"De Sousa Ribeiro","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","first-page":"7390","article-title":"High fidelity image counterfactuals with probabilistic causal models","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","author":"De Sousa Ribeiro","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.strusafe.2008.06.020"},{"key":"ref19","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Nice: Nonlinear independent components estimation","author":"Dinh","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref21","article-title":"Density estimation using real NVP","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dinh","year":"2017"},{"key":"ref22","article-title":"Variational flow matching for graph generation","volume-title":"Proceedings of the Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS)","author":"Eijkelboom","year":"2024"},{"key":"ref23","article-title":"Refuge2 challenge: A treasure trove for multidimension analysis and evaluation in glaucoma screening","author":"Fang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Modeling multimodal aleatoric uncertainty in segmentation with mixture of stochastic experts","volume-title":"International Conference on Learning Representations (ICLR)","author":"Gao","year":"2022"},{"key":"ref25","article-title":"Modeling multimodal aleatoric uncertainty in segmentation with mixture of stochastic experts","volume-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR)","author":"Gao","year":"2023"},{"key":"ref26","first-page":"881","article-title":"Made: Masked autoencoder for distribution estimation","volume-title":"International Conference on Machine Learning (ICML)","author":"Germain","year":"2015"},{"key":"ref27","article-title":"From variational to deterministic autoencoders","volume-title":"International Conference on Learning Representations (ICLR)","author":"Ghosh","year":"2020"},{"key":"ref28","article-title":"Starflow: Scaling latent normalizing flows for high-resolution image synthesis","author":"Gu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/BF00699039"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/168304.168306"},{"key":"ref31","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hu","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680628"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10463-023-00884-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-018-5695-5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295309"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00781"},{"key":"ref38","article-title":"Glow: Generative flow with invertible $1 \\times 1$ convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"Auto-encoding variational bayes","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kingma","year":"2014"},{"key":"ref40","article-title":"Improved variational inference with inverse autoregressive flow","volume":"29","author":"Kingma","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","article-title":"Position: Uncertainty quantification needs reassessment for large language model agents","volume-title":"Forty-second International Conference on Machine Learning (ICML) Position Paper Track","author":"Kirchhof","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref43","article-title":"A probabilistic u-net for segmentation of ambiguous images","volume":"31","author":"Kohl","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","article-title":"A hierarchical probabilistic u-net for modeling multi-scale ambiguities","author":"Kohl","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2019.106816"},{"key":"ref46","article-title":"Structured uncertainty in the observation space of variational autoencoders","author":"Langley","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref47","article-title":"Position: Supervised classifiers answer the wrong questions for OOD detection","volume-title":"Forty-second International Conference on Machine Learning (ICML) Position Paper Track","author":"Li","year":"2025"},{"key":"ref48","article-title":"Flow matching for generative modeling","volume-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR)","author":"Lipman","year":"2023"},{"key":"ref49","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR)","author":"Liu","year":"2023"},{"key":"ref50","article-title":"Don\u2019t blame the elbo! a linear vae perspective on posterior collapse","volume":"32","author":"Lucas","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref52","volume-title":"Bayesian methods for adaptive models","author":"Mackay","year":"1992"},{"key":"ref53","article-title":"Predictive uncertainty estimation via prior networks","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"31","author":"Malinin","year":"2018"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04984-1_12"},{"key":"ref55","first-page":"12756","article-title":"Stochastic segmentation networks: Modelling spatially correlated aleatoric uncertainty","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Monteiro","year":"2020"},{"key":"ref56","article-title":"Measuring axiomatic soundness of counterfactual image models","volume-title":"Proceedings of the Eleventh International Conference on Learning Representations (ICLR)","author":"Monteiro","year":"2023"},{"key":"ref57","article-title":"Probabilistic inference using markov chain monte carlo methods","volume-title":"Technical report","author":"Neal","year":"1993"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1613"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2007"},{"key":"ref60","first-page":"3918","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Oord","year":"2018"},{"key":"ref61","article-title":"Masked autoregressive flow for density estimation","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"30","author":"Papamakarios","year":"2017"},{"issue":"57","key":"ref62","first-page":"1","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"ref63","first-page":"39556","article-title":"Position: Bayesian deep learning is needed in the age of large-scale AI","volume-title":"Proceedings of the 41st International Conference on Machine Learning (ICML)","author":"Papamarkou","year":"2024"},{"key":"ref64","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"32","author":"Paszke","year":"2019"},{"key":"ref65","volume-title":"Non-denoising forward-time diffusions","author":"Peluchetti","year":"2022"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01110"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01061"},{"key":"ref68","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Rezende","year":"2015"},{"key":"ref69","article-title":"Taming vaes","author":"Rezende","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref70","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Rezende","year":"2014"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1561\/0600000113"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref73","first-page":"606","article-title":"The effective rank: A measure of effective dimensionality","volume-title":"Proceedings of the 2007 15th European Signal Processing Conference (EUSIPCO). IEEE","author":"Roy","year":"2007"},{"key":"ref74","article-title":"PixelCNN++: Improving the pixelCNN with discretized logistic mixture likelihood and other modifications","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Salimans","year":"2017"},{"key":"ref75","volume-title":"The KL approximation","author":"Schulman","year":"2017"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59861-7_9"},{"key":"ref77","article-title":"Evidential deep learning to quantify classification uncertainty","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"31","author":"Sensoy","year":"2018"},{"key":"ref78","article-title":"Diffusion schr\u00f6dinger bridge matching","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"36","author":"Shi","year":"2024"},{"key":"ref79","article-title":"Rethinking aleatoric and epistemic uncertainty","author":"Smith","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref80","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Sohl-Dickstein","year":"2015"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.21423"},{"key":"ref82","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref83","article-title":"Jetformer: An autoregressive generative model of raw images and text","volume-title":"Proceedings of the Thirteenth International Conference on Learning Representations (ICLR)","author":"Tschannen","year":"2025"},{"key":"ref84","article-title":"Prior and posterior networks: A survey on evidential deep learning methods for uncertainty estimation","author":"Ulmer","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref85","first-page":"19667","article-title":"Nvae: A deep hierarchical variational autoencoder","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"33","author":"Vahdat","year":"2020"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87735-4_8"},{"key":"ref87","article-title":"Conditional image generation with pixelcnn decoders","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","volume":"29","author":"van den Oord","year":"2016"},{"key":"ref88","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"van den Oord","year":"2016"},{"key":"ref89","first-page":"1623","article-title":"Medsegdiff: Medical image segmentation with diffusion probabilistic model","volume-title":"Proceedings of Medical Imaging with Deep Learning (MIDL)","author":"Wu","year":"2024"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00423"},{"key":"ref91","article-title":"Breaking the softmax bottleneck: A high-rank RNN language model","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Yang","year":"2018"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00109"},{"key":"ref93","article-title":"That label\u2019s got style: Handling label style bias for uncertain image segmentation","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Zepf","year":"2023"},{"key":"ref94","article-title":"Normalizing flows are capable generative models","volume-title":"Proceedings of the Forty-second International Conference on Machine Learning (ICML)","author":"Zhai","year":"2025"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548060"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548115"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.108238"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.179"},{"key":"ref99","article-title":"Spa: Efficient user-preference alignment against uncertainty in medical image segmentation","author":"Zhu","year":"2024","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445978.pdf?arnumber=11445978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:25:46Z","timestamp":1777613146000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":99,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01369","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}