Bayesian Deep

Bayesian deep learning aims to improve the reliability and interpretability of deep neural networks by incorporating probabilistic methods. Current research focuses on developing and refining Bayesian approaches for uncertainty quantification, exploring various model architectures (including deep ensembles, variational inference, and Hamiltonian Monte Carlo) and priors (like horseshoe and heavy-tailed distributions) to achieve better calibrated uncertainty estimates. This field is significant because reliable uncertainty quantification is crucial for deploying deep learning models in high-stakes applications like medical image analysis and robotics, where understanding model confidence is paramount for safe and effective decision-making.

Papers

July 16, 2024

On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss
Mohammed Fellaji, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro
Calibration Performance Epistemic Uncertainty Deep Ensemble General Principle Fermi Paradox Bayesian Deep

June 24, 2024

Horseshoe-type Priors for Independent Component Estimation
Jyotishka Datta, Nicholas G. Polson
Expectation Maximization Independent Component Analysis Bayesian Posterior Bayesian Deep Full Bayesian

June 5, 2024

Posterior and variational inference for deep neural networks with heavy-tailed weights
Ismaël Castillo, Paul Egels
Deep Neural Network Variational Inference Heavy Tailed Prior Distribution Posterior Mode Bayesian Deep

March 28, 2024

Improving Cancer Imaging Diagnosis with Bayesian Networks and Deep Learning: A Bayesian Deep Learning Approach
Pei Xi, Lin
Deep Learning Machine Learning Bayesian Network Bayesian Deep Learning Tumor Cell Bayesian Deep

March 4, 2024

Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation
Yidong Zhao, Joao Tourais, Iain Pierce, Christian Nitsche, Thomas A. Treibel, Sebastian Weingärtner, Artur M. Schweidtmann, Qian Tao
Financial Application Medical Image Segmentation Task Hamiltonian Monte Carlo Bayesian Uncertainty Segmentation Uncertainty Deep Learning Based Medical Bayesian Deep Deep Bayesian

February 12, 2024

Bayesian Deep Learning Via Expectation Maximization and Turbo Deep Approximate Message Passing
Wei Xu, An Liu, Yiting Zhang, Vincent Lau
Model Compression Bayesian Deep Learning Approximate Message Bayesian Deep Global Posterior Sparse Bayesian

November 23, 2022

Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks
Neil Band, Tim G. J. Rudner, Qixuan Feng, Angelos Filos, Zachary Nado, Michael W. Dusenberry, Ghassen Jerfel, Dustin Tran, Yarin Gal
Fundus Image Diabetic Retinopathy Bayesian Deep Learning Vision Benchmark Bayesian Deep

July 19, 2022

Decorrelative Network Architecture for Robust Electrocardiogram Classification
Christopher Wiedeman, Ge Wang
Adversarial Attack Adversarial Sample Feature Decorrelation ECG Classification Novel Ensemble Bayesian Deep Bayesian Ensemble

June 18, 2022

Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation
Jianfeng Wang, Thomas Lukasiewicz
Semi Supervised Medical Image Segmentation Bayesian Deep Learning Bayesian Deep Bayesian Generative Model

February 23, 2022

Using Bayesian Deep Learning to infer Planet Mass from Gaps in Protoplanetary Disks
Sayantan Auddy, Ramit Dey, Min-Kai Lin, Daniel Carrera, Jacob B. Simon
Filling Gap Bayesian Deep Learning Protoplanetary Disk Bayesian Deep

February 22, 2022

UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography
Francisca Vasconcelos, Bobby He, Nalini Singh, Yee Whye Teh
Uncertainty Quantification Computed Tomography Neural Implicit Representation Accurate Reconstruction Model Based Prior Bayesian Deep

February 19, 2022

Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks
Jurijs Nazarovs, Ronak R. Mehta, Vishnu Suresh Lokhande, Vikas Singh
Computer Vision Uncertainty Estimation Deep Model Monte Carlo Reparameterization Method Computation Graph Bayesian Deep

December 16, 2021

On the Uncertain Single-View Depths in Colonoscopies
Javier Rodríguez-Puigvert, David Recasens, Javier Civera, Rubén Martínez-Cantín
Depth Estimation Depth Network Single View Depth Colonoscopy Data Bayesian Deep

Bayesian Deep

Papers

On the Calibration of Epistemic Uncertainty: Principles, Paradoxes and Conflictual Loss

Horseshoe-type Priors for Independent Component Estimation

Posterior and variational inference for deep neural networks with heavy-tailed weights

Improving Cancer Imaging Diagnosis with Bayesian Networks and Deep Learning: A Bayesian Deep Learning Approach

Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentation

Bayesian Deep Learning Via Expectation Maximization and Turbo Deep Approximate Message Passing

Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks

Decorrelative Network Architecture for Robust Electrocardiogram Classification

Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation

Using Bayesian Deep Learning to infer Planet Mass from Gaps in Protoplanetary Disks

UncertaINR: Uncertainty Quantification of End-to-End Implicit Neural Representations for Computed Tomography

Graph Reparameterizations for Enabling 1000+ Monte Carlo Iterations in Bayesian Deep Neural Networks

On the Uncertain Single-View Depths in Colonoscopies