Calibrating Deep Convolutional Gaussian Processes
Not on the map. Why?
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.
Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 May 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 4; 2023: 1; 2024: 2; 2025: 2.
13 papers.
Sort:
- 2021The Promises and Pitfalls of Deep Kernel Learningcited by 81
- 2021Classifier Calibration: A survey on how to assess and improve predicted class probabilitiescited by 73
- 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
- 2022Modular Conformal Calibrationcited by 15
- 2021Should Ensemble Members Be Calibrated?cited by 11
- 2022Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Processcited by 5
- 2024Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equationscited by 4
- 2022Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGANcited by 2
- 2024Interventional Processes for Causal Uncertainty Quantificationcited by 2
- 2021Confidence Calibration with Bounded Error Using Transformationscited by 0
- 2023Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimationcited by 0
- 2025Scalable Deep Basis Kernel Gaussian Processescited by 0
- 2025DTI-GP: Bayesian operations for drug-target interactions using deep kernel Gaussian processes31 Dec 2025
- 2025Scalable Deep Basis Kernel Gaussian Processes24 May 2025
- 2024Interventional Processes for Causal Uncertainty Quantification18 Oct 2024
- 2024Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equations12 Aug 2024
- 2023Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimation13 Dec 2023
- 2022Modular Conformal Calibration23 Jun 2022
- 2022Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process13 Jun 2022
- 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness1 May 2022
- 2022Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN23 Apr 2022
- 2021Classifier Calibration: A survey on how to assess and improve predicted class probabilities20 Dec 2021
- 2021Confidence Calibration with Bounded Error Using Transformations25 Feb 2021
- 2021The Promises and Pitfalls of Deep Kernel Learning24 Feb 2021
1 more
- 2021Should Ensemble Members Be Calibrated?13 Jan 2021
- 2021The Promises and Pitfalls of Deep Kernel Learningcited by 81
- 2021Classifier Calibration: A survey on how to assess and improve predicted class probabilitiescited by 73
- 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
- 2022Modular Conformal Calibrationcited by 15
- 2021Should Ensemble Members Be Calibrated?cited by 11
- 2022Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Processcited by 5
- 2024Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equationscited by 4
- 2022Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGANcited by 2
- 2024Interventional Processes for Causal Uncertainty Quantificationcited by 2
- 2021Confidence Calibration with Bounded Error Using Transformationscited by 0
- 2023Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimationcited by 0
- 2025Scalable Deep Basis Kernel Gaussian Processescited by 0
12 most cited of 13 All 13 (JSON)
- 2025DTI-GP: Bayesian operations for drug-target interactions using deep kernel Gaussian processes31 Dec 2025
- 2025Scalable Deep Basis Kernel Gaussian Processes24 May 2025
- 2024Interventional Processes for Causal Uncertainty Quantification18 Oct 2024
- 2024Fully Bayesian Differential Gaussian Processes through Stochastic Differential Equations12 Aug 2024
- 2023Meta-learning to Calibrate Gaussian Processes with Deep Kernels for Regression Uncertainty Estimation13 Dec 2023
- 2022Modular Conformal Calibration23 Jun 2022
- 2022Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process13 Jun 2022
- 2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness1 May 2022
- 2022Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN23 Apr 2022
- 2021Classifier Calibration: A survey on how to assess and improve predicted class probabilities20 Dec 2021
- 2021Confidence Calibration with Bounded Error Using Transformations25 Feb 2021
- 2021The Promises and Pitfalls of Deep Kernel Learning24 Feb 2021
12 newest of 13 All 13 (JSON)