Paper Info
Title
Learning For Single-Shot Confidence Calibration In Deep Neural Networks Through Stochastic Inferences
Abstract
We propose a generic framework to calibrate accuracy and confidence of a prediction in deep neural networks through stochastic inferences. We interpret stochastic regularization using a Bayesian model, and analyze the relation between predictive uncertainty of networks and variance of the prediction scores obtained by stochastic inferences for a single example. Our empirical study shows that the accuracy and the score of a prediction are highly correlated with the variance of multiple stochastic inferences given by stochastic depth or dropout. Motivated by this observation, we design a novel variance-weighted confidence-integrated loss function that is composed of two cross-entropy loss terms with respect to ground-truth and uniform distribution, which are balanced by variance of stochastic prediction scores. The proposed loss function enables us to learn deep neural networks that predict confidence calibrated scores using a single inference. Our algorithm presents outstanding confidence calibration performance and improves classification accuracy when combined with two popular stochastic regularization techniques stochastic depth and dropout in multiple models and datasets; it alleviates overconfidence issue in deep neural networks significantly by training networks to achieve prediction accuracy proportional to confidence of prediction.
Year
DOI
Venue
2019
10.1109/CVPR.2019.00924
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
Field
DocType
ISSN
Bayesian inference,Inference,Uniform distribution (continuous),Regularization (mathematics),Artificial intelligence,Overconfidence effect,Calibration,Machine learning,Mathematics,Empirical research,Deep neural networks
Conference
1063-6919
Citations 
PageRank 
References 
2
0.36
0
Authors
3
Name
Order
Citations
PageRank
Seonguk Seo1181.95
Paul Hongsuck Seo221.04
Bohyung Han3220394.45