# Calibrating Deep Convolutional Gaussian Processes

arXiv: https://arxiv.org/abs/1805.10522 · HTML: https://mlsanity.com/paper/1805.10522/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2018.

## Built on by (most cited first, 13 of 13)

- [The Promises and Pitfalls of Deep Kernel Learning](https://mlsanity.com/paper/2102.12108/) (2021)
- [Classifier Calibration: A survey on how to assess and improve predicted class probabilities](https://mlsanity.com/paper/2112.10327/) (2021)
- [A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness](https://mlsanity.com/paper/2205.00403/) (2022)
- [Modular Conformal Calibration](https://mlsanity.com/paper/2206.11468/) (2022)
- [Should Ensemble Members Be Calibrated?](https://mlsanity.com/paper/2101.05397/) (2021)
- [Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process](https://mlsanity.com/paper/2206.06357/) (2022)
- [Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equations](https://mlsanity.com/paper/2408.06069/) (2024)
- [Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN](https://mlsanity.com/paper/2204.10970/) (2022)
- [Interventional Processes for Causal Uncertainty Quantification](https://mlsanity.com/paper/2410.14483/) (2024)
- [Confidence Calibration with Bounded Error Using Transformations](https://mlsanity.com/paper/2102.12680/) (2021)
- [Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimation](https://mlsanity.com/paper/2312.07952/) (2023)
- [Scalable Deep Basis Kernel Gaussian Processes](https://mlsanity.com/paper/2505.18526/) (2025)
- [DTI-GP: Bayesian operations for drug-target interactions using deep kernel Gaussian processes](https://mlsanity.com/paper/2512.24810/) (2025)

## Abstract (arXiv)

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.