mlsanityData to 7 Oct 2026

An Uncertainty-aware Loss Function for Training Neural Networks with Calibrated Predictions

arXiv 2110.03260 ↗First posted 7 Oct 2021cs.LG cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Uncertainty quantification of machine learning and deep learning methods plays an important role in enhancing trust to the obtained result. In recent years, a numerous number of uncertainty quantification methods have been introduced. Monte Carlo dropout (MC-Dropout) is one of the most well-known techniques to quantify uncertainty in deep learning methods. In this study, we propose two new loss functions by combining cross entropy with Expected Calibration Error (ECE) and Predictive Entropy (PE). The obtained results clearly show that the new proposed loss functions lead to having a calibrated MC-Dropout method. Our results confirmed the great impact of the new hybrid loss functions for minimising the overlap between the distributions of uncertainty estimates for correct and incorrect predictions without sacrificing the model's overall performance.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 24 of its 50 references that are in the map. First posted on arXiv 7 Oct 2021.

Builds on

24 of 50 references.

References · 24

  1. 2017On Calibration of Modern Neural Networkscited by 4,860
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  6. 2021SleepTransformer: Automatic Sleep Staging with Interpretability and Uncertainty Quantificationcited by 83
  7. 2020Uncertainty Quantification Using Neural Networks for Molecular Property Predictioncited by 66
  8. 2019Uncertainty Quantification in Deep MRI Reconstructioncited by 49
  9. 2018Deep Directional Statistics: Pose Estimation with Uncertainty Quantificationcited by 45
  10. 2017Bayesian Image Quality Transfer with CNNs: Exploring Uncertainty in dMRI Super-Resolutioncited by 29
  11. 2021A Vision-based System for Traffic Anomaly Detection using Deep Learning and Decision Treescited by 26
  12. 2020An Uncertainty-aware Transfer Learning-based Framework for Covid-19 Diagnosiscited by 22
12 more
  1. 2020Objective Evaluation of Deep Uncertainty Predictions for COVID-19 Detectioncited by 20
  2. 2021I Find Your Lack of Uncertainty in Computer Vision Disturbingcited by 16
  3. 2020Uncertainty Quantification for Sparse Deep Learningcited by 13
  4. 2021Uncertainty Quantification by Ensemble Learning for Computational Optical Form Measurementscited by 11
  5. 2021Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Drivingcited by 10
  6. 2021Uncertainty-Aware Credit Card Fraud Detection Using Deep Learningcited by 10
  7. 2021UncertaintyFuseNet: Robust Uncertainty-aware Hierarchical Feature Fusion Model with Ensemble Monte Carlo Dropout for COVID-19 Detectioncited by 8
  8. 2020Detecting Adversarial Examples for Speech Recognition via Uncertainty Quantificationcited by 7
  9. 2017Uncertainty-Aware Organ Classification for Surgical Data Science Applications in Laparoscopycited by 6
  10. 2020Uncertainty Quantification for Deep Context-Aware Mobile Activity Recognition and Unknown Context Discoverycited by 6
  11. 2021Confidence Aware Neural Networks for Skin Cancer Detectioncited by 5
  12. 2018Informed MCMC with Bayesian Neural Networks for Facial Image Analysiscited by 3

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024Error-Driven Uncertainty Aware Trainingcited by 3
  2. 2025Uncertainty Estimation by Human Perception versus Neural Modelscited by 3
  3. 2025CLUE: Neural Networks Calibration via Learning Uncertainty-Error alignmentcited by 2
  4. 2024Enhanced Uncertainty Estimation in Ultrasound Image Segmentation with MSU-Netcited by 1
  5. 2024The Craft of Selective Prediction: Towards Reliable Case Outcome Classification -- An Empirical Study on European Court of Human Rights Casescited by 1
  6. 2024Beyond Uncertainty Quantification: Learning Uncertainty for Trust-Informed Neural Network Decisions - A Case Study in COVID-19 Classificationcited by 0