Robust Uncertainty

Robust uncertainty estimation in deep learning aims to accurately quantify the confidence of model predictions, particularly when encountering out-of-distribution data or noisy inputs. Current research focuses on developing methods that integrate diverse techniques, such as Bayesian neural networks, Monte Carlo dropout, and conformal prediction, often within modified or ensemble architectures, to improve the reliability and robustness of uncertainty quantification across various tasks (e.g., image classification, regression, segmentation). This is crucial for deploying deep learning models in safety-critical applications like medical imaging and autonomous systems, where understanding and managing uncertainty is paramount for reliable and trustworthy performance.

Papers

October 29, 2024

On the Robustness of Adversarial Training Against Uncertainty Attacks
Emanuele Ledda, Giovanni Scodeller, Daniele Angioni, Giorgio Piras, Antonio Emanuele Cinà, Giorgio Fumera, Battista Biggio, Fabio Roli
Native Robustness Adversarial Example Adversarial Training Reliable Uncertainty Robust Uncertainty

March 1, 2024

SURE: SUrvey REcipes for building reliable and robust deep networks
Yuting Li, Yingyi Chen, Xuanlong Yu, Dexiong Chen, Xi Shen
Uncertainty Estimation Robust Deep Prediction Uncertainty Yes Yes Robust Uncertainty Uncertainty Estimation Performance

November 24, 2023

Bayesian Neural Networks for 2D MRI Segmentation
Lohith Konathala
Semantic Segmentation Segmentation Uncertainty Interpretable Segmentation Robust Uncertainty

November 18, 2023

Estimating Uncertainty in Landslide Segmentation Models
Savinay Nagendra, Chaopeng Shen, Daniel Kifer
Uncertainty Estimation Pixel Wise Uncertainty Landslide Detection Robust Uncertainty

November 16, 2023

On the Quantification of Image Reconstruction Uncertainty without Training Data
Sirui Bi, Victor Fung, Jiaxin Zhang
Training Data Inverse Problem Computational Imaging Robust Uncertainty Reconstruction Uncertainty

September 20, 2023

Conformalized Multimodal Uncertainty Regression and Reasoning
Domenico Parente, Nastaran Darabi, Alex C. Stutts, Theja Tulabandhula, Amit Ranjan Trivedi
Complex Reasoning Uncertainty Quantification Optical Flow Visual Odometry Robust Uncertainty Multimodal Uncertainty

August 17, 2023

Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression
Xuanlong Yu, Gianni Franchi, Jindong Gu, Emanuel Aldea
Native Robustness Uncertainty Quantification Novel Regression Auxiliary Objective Robust Uncertainty Dirichlet Prior

July 3, 2023

Robust Uncertainty Estimation for Classification of Maritime Objects
Jonathan Becktor, Frederik Scholler, Evangelos Boukas, Lazaros Nalpantidis
Classification Code Uncertainty Estimation Reaction Ship Uncertainty Measure Robust Uncertainty Class Uncertainty Ship Dataset

February 28, 2023

Toward Robust Uncertainty Estimation with Random Activation Functions
Yana Stoyanova, Soroush Ghandi, Maryam Tavakol
Uncertainty Quantification Ensemble Model Ensemble Diversity Robust Uncertainty Ensemble Uncertainty

October 3, 2022

On Attacking Out-Domain Uncertainty Estimation in Deep Neural Networks
Huimin Zeng, Zhenrui Yue, Yang Zhang, Ziyi Kou, Lanyu Shang, Dong Wang
Deep Neural Network Uncertainty Estimation Parameter Uncertainty Reliable Uncertainty Robust Uncertainty State of the Art Uncertainty

March 29, 2022

Gaussian Control Barrier Functions : A Non-Parametric Paradigm to Safety
Mouhyemen Khan, Tatsuya Ibuki, Abhijit Chatterjee
Gaussian Process Control Barrier Function Human SAFETY CBF Based Robust Uncertainty

January 15, 2022

Robust uncertainty estimates with out-of-distribution pseudo-inputs training
Pierre Segonne, Yevgen Zainchkovskyy, Søren Hauberg
Probabilistic Model Model Uncertainty Predictive Uncertainty Uncertainty Prediction Pseudo Labeled Robust Uncertainty

November 11, 2021

On Efficient Uncertainty Estimation for Resource-Constrained Mobile Applications
Johanna Rock, Tiago Azevedo, René de Jong, Daniel Ruiz-Muñoz, Partha Maji
Uncertainty Estimation Deep Ensemble Predictive Uncertainty Fast Inference Efficient Uncertainty Estimation Robust Uncertainty