BaCOUn: Bayesian Classifers with Out-of-Distribution Uncertainty
arXiv:2007.06096
Abstract
Traditional training of deep classifiers yields overconfident models that are not reliable under dataset shift. We propose a Bayesian framework to obtain reliable uncertainty estimates for deep classifiers. Our approach consists of a plug-in "generator" used to augment the data with an additional class of points that lie on the boundary of the training data, followed by Bayesian inference on top of features that are trained to distinguish these "out-of-distribution" points.
arXiv commentICML 2020 Workshop on Uncertainty and Robustness in Deep Learning
References in corpus (9)
- Scikit-learn: Machine Learning in Python
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Auto-Encoding Variational Bayes
- Variational Inference with Normalizing Flows
- Density estimation using Real NVP
- EMNIST: an extension of MNIST to handwritten letters
- Out-of-distribution Detection in Classifiers via Generation
- Building robust classifiers through generation of confident out of distribution examples
- Analysis of Confident-Classifiers for Out-of-distribution Detection