Calibration of Model Uncertainty for Dropout Variational Inference
The model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. In this paper, different logit scaling methods are extended to dropout variational inference to recalibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration. The effectiveness of recalibration is evaluated on CIFAR-10/100 and SVHN for recent CNN architectures. Experimental results show that logit scaling considerably reduce miscalibration by means of UCE. Well-calibrated uncertainty enables reliable rejection of uncertain predictions and robust detection of out-of-distribution data.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceVariational InferenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Well-calibrated Model Uncertainty with Temperature Scaling for Dropout Variational Inference
Model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. The uncertainty does not represent the model error well. In this paper, temperature scaling is extended to…
Bayesian InferenceVariational InferenceRobustly representing uncertainty in deep neural networks through sampling
As deep neural networks (DNNs) are applied to increasingly challenging problems, they will need to be able to represent their own uncertainty. Modeling uncertainty is one of the key features of Bayesian methods. Using Be…
Variational InferenceGFlowOut: Dropout with Generative Flow Networks
Bayesian Inference offers principled tools to tackle many critical problems with modern neural networks such as poor calibration and generalization, and data inefficiency. However, scaling Bayesian inference to large arc…
Bayesian InferenceVariational InferenceRecalibration of Aleatoric and Epistemic Regression Uncertainty in Medical Imaging
The consideration of predictive uncertainty in medical imaging with deep learning is of utmost importance. We apply estimation of both aleatoric and epistemic uncertainty by variational Bayesian inference with Monte Carl…
Bayesian InferenceregressionFederated Learning via Meta-Variational Dropout
Federated Learning (FL) aims to train a global inference model from remotely distributed clients, gaining popularity due to its benefit of improving data privacy. However, traditional FL often faces challenges in practic…
Federated Learning