Calibrating Deep Convolutional Gaussian Processes
arXiv:1805.10522
Abstract
The wide adoption of Convolutional Neural Networks (CNNs) in applications where decision-making under uncertainty is fundamental, has brought a great deal of attention to the ability of these models to accurately quantify the uncertainty in their predictions. Previous work on combining CNNs with Gaussian processes (GPs) has been developed under the assumption that the predictive probabilities of these models are well-calibrated. In this paper we show that, in fact, current combinations of CNNs and GPs are miscalibrated. We proposes a novel combination that considerably outperforms previous approaches on this aspect, while achieving state-of-the-art performance on image classification tasks.
arXiv comment12 pages
References in corpus (7)
- Auto-Encoding Variational Bayes
- What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
- On Calibration of Modern Neural Networks
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
- Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks
- Orthogonal Random Features
- Random Feature Expansions for Deep Gaussian Processes
Cited by in corpus (5)
- A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
- Classifier Calibration: A survey on how to assess and improve predicted class probabilities
- Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
- Deep Gaussian Processes with Convolutional Kernels
- Exploring the Uncertainty Properties of Neural Networks' Implicit Priors in the Infinite-Width Limit