Uncertainty Estimation Comparison Hub
4 papers - avg viability 6.5
Top Papers
- CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Model(8.0)
CUPID is a plug-in framework that enables joint estimation of aleatoric and epistemic uncertainty in deep learning models without retraining.
- Efficient Credal Prediction through Decalibration(7.0)
Efficiently estimate uncertainty in machine learning models by predicting probability intervals, enabling safer deployment in critical applications.
- To Predict or Not to Predict? Towards reliable uncertainty estimation in the presence of noise(7.0)
Improve the reliability of multilingual text classification by integrating uncertainty estimation, allowing systems to abstain from predicting on uncertain instances and boost overall accuracy.
- Beyond Accuracy: Reliability and Uncertainty Estimation in Convolutional Neural Networks(4.0)
A comparative study on uncertainty estimation methods in deep neural networks to enhance reliability in predictions.