mlsanityData to 14 Oct 2026

Fully Bayesian VIB-DeepSSM

arXiv 2305.05797 ↗First posted 9 May 2023cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Statistical shape modeling (SSM) enables population-based quantitative analysis of anatomical shapes, informing clinical diagnosis. Deep learning approaches predict correspondence-based SSM directly from unsegmented 3D images but require calibrated uncertainty quantification, motivating Bayesian formulations. Variational information bottleneck DeepSSM (VIB-DeepSSM) is an effective, principled framework for predicting probabilistic shapes of anatomy from images with aleatoric uncertainty quantification. However, VIB is only half-Bayesian and lacks epistemic uncertainty inference. We derive a fully Bayesian VIB formulation and demonstrate the efficacy of two scalable implementation approaches: concrete dropout and batch ensemble. Additionally, we introduce a novel combination of the two that further enhances uncertainty calibration via multimodal marginalization. Experiments on synthetic shapes and left atrium data demonstrate that the fully Bayesian VIB network predicts SSM from images with improved uncertainty reasoning without sacrificing accuracy.

Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). Builds on 21 of its 31 references that are in the map. First posted on arXiv 9 May 2023.

Builds on

21 of 31 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  3. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  4. 2016Deep Variational Information Bottleneckcited by 930
  5. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 560
  6. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  7. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 443
  8. 2020BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learningcited by 371
  9. 2017Concrete Dropoutcited by 227
  10. 2020Uncertainty Quantification and Deep Ensemblescited by 139
  11. 2022On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networkscited by 120
  12. 2020The Case for Bayesian Deep Learningcited by 69
9 more
  1. 2019Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detectioncited by 35
  2. 2018DeepSSM: A Deep Learning Framework for Statistical Shape Modeling from Raw Imagescited by 32
  3. 2020Uncertain-DeepSSM: From Images to Probabilistic Shape Modelscited by 20
  4. 2022From Images to Probabilistic Anatomical Shapes: A Deep Variational Bottleneck Approachcited by 17
  5. 2020Probabilistic 3D surface reconstruction from sparse MRI informationcited by 12
  6. 2018Uncertainty Quantification in CNN-Based Surface Prediction Using Shape Priorscited by 9
  7. 2018Deep Learning for End-to-End Atrial Fibrillation Recurrence Estimationcited by 6
  8. 2020VIB is Half Bayescited by 2
  9. 2019Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scalescited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 5; 2025: 1; 2026: 1.

11 papers.

  1. 2023Point2SSM: Learning Morphological Variations of Anatomies from Point Cloudcited by 14
  2. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 14
  3. 2024Point2SSM++: Self-Supervised Learning of Anatomical Shape Models from Point Cloudscited by 5
  4. 2023ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Imagescited by 4
  5. 2023Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentationcited by 4
  6. 2024Weakly Supervised Bayesian Shape Modeling from Unsegmented Medical Imagescited by 4
  7. 2024SCorP: Statistics-Informed Dense Correspondence Prediction Directly from Unsegmented Medical Imagescited by 3
  8. 2023Progressive DeepSSM: Training Methodology for Image-To-Shape Deep Modelscited by 2
  9. 2024Optimization-Driven Statistical Models of Anatomies using Radial Basis Function Shape Representationcited by 1
  10. 2024Probabilistic 3D Correspondence Prediction from Sparse Unsegmented Imagescited by 0
  11. 2026Uncertainty Quantification for Cardiac Shape Reconstruction with Deep Signed Distance Functions via MCMC methodscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021DeepSSM: A Blueprint for Image-to-Shape Deep Learning Models
  2. 2025Mesh2SSM++: A Probabilistic Framework for Unsupervised Learning of Statistical Shape Model of Anatomies from Surface Meshes
  3. 2023Mesh2SSM: From Surface Meshes to Statistical Shape Models of Anatomy
  4. 2024MASSM: An End-to-End Deep Learning Framework for Multi-Anatomy Statistical Shape Modeling Directly From Images
  5. 2023S3M: Scalable Statistical Shape Modeling through Unsupervised Correspondences
  6. 2021Deep Implicit Statistical Shape Models for 3D Medical Image Delineation
  7. 2023Image2SSM: Reimagining Statistical Shape Models from Images with Radial Basis Functions
  8. 2024On the Viability of Semi-Supervised Segmentation Methods for Statistical Shape Modeling