# Fully Bayesian VIB-DeepSSM

arXiv: https://arxiv.org/abs/2305.05797 · HTML: https://mlsanity.com/paper/2305.05797/

## 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 (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [A Simple Baseline for Bayesian Uncertainty in Deep Learning](https://mlsanity.com/paper/1902.02476/) (2019)
- [Bayesian Deep Learning and a Probabilistic Perspective of Generalization](https://mlsanity.com/paper/2002.08791/) (2020)
- [Deep Ensembles: A Loss Landscape Perspective](https://mlsanity.com/paper/1912.02757/) (2019)
- [BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning](https://mlsanity.com/paper/2002.06715/) (2020)
- [Concrete Dropout](https://mlsanity.com/paper/1705.07832/) (2017)
- [Uncertainty Quantification and Deep Ensembles](https://mlsanity.com/paper/2007.08792/) (2020)
- [On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks](https://mlsanity.com/paper/2203.09168/) (2022)
- [The Case for Bayesian Deep Learning](https://mlsanity.com/paper/2001.10995/) (2020)
- [Bayesian Variational Autoencoders for Unsupervised Out-of-Distribution Detection](https://mlsanity.com/paper/1912.05651/) (2019)
- [DeepSSM: A Deep Learning Framework for Statistical Shape Modeling from Raw Images](https://mlsanity.com/paper/1810.00111/) (2018)
- [Uncertain-DeepSSM: From Images to Probabilistic Shape Models](https://mlsanity.com/paper/2007.06516/) (2020)
- [From Images to Probabilistic Anatomical Shapes: A Deep Variational Bottleneck Approach](https://mlsanity.com/paper/2205.06862/) (2022)
- [Probabilistic 3D surface reconstruction from sparse MRI information](https://mlsanity.com/paper/2010.02041/) (2020)
- [Uncertainty Quantification in CNN-Based Surface Prediction Using Shape Priors](https://mlsanity.com/paper/1807.11272/) (2018)
- [Deep Learning for End-to-End Atrial Fibrillation Recurrence Estimation](https://mlsanity.com/paper/1810.00475/) (2018)
- [VIB is Half Bayes](https://mlsanity.com/paper/2011.08711/) (2020)
- [Unifying Variational Inference and PAC-Bayes for Supervised Learning that Scales](https://mlsanity.com/paper/1910.10367/) (2019)

## Built on by (most cited first, 11 of 11)

- [Point2SSM: Learning Morphological Variations of Anatomies from Point Cloud](https://mlsanity.com/paper/2305.14486/) (2023)
- [Uncertainty Quantification for Machine Learning in Healthcare: A Survey](https://mlsanity.com/paper/2505.02874/) (2025)
- [Point2SSM++: Self-Supervised Learning of Anatomical Shape Models from Point Clouds](https://mlsanity.com/paper/2405.09707/) (2024)
- [ADASSM: Adversarial Data Augmentation in Statistical Shape Models From Images](https://mlsanity.com/paper/2307.03273/) (2023)
- [Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentation](https://mlsanity.com/paper/2308.07506/) (2023)
- [Weakly Supervised Bayesian Shape Modeling from Unsegmented Medical Images](https://mlsanity.com/paper/2405.09697/) (2024)
- [SCorP: Statistics-Informed Dense Correspondence Prediction Directly from Unsegmented Medical Images](https://mlsanity.com/paper/2404.17967/) (2024)
- [Progressive DeepSSM: Training Methodology for Image-To-Shape Deep Models](https://mlsanity.com/paper/2310.01529/) (2023)
- [Optimization-Driven Statistical Models of Anatomies using Radial Basis Function Shape Representation](https://mlsanity.com/paper/2411.15882/) (2024)
- [Probabilistic 3D Correspondence Prediction from Sparse Unsegmented Images](https://mlsanity.com/paper/2407.01931/) (2024)
- [Uncertainty Quantification for Cardiac Shape Reconstruction with Deep Signed Distance Functions via MCMC methods](https://mlsanity.com/paper/2605.07987/) (2026)

## 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.