# Confidence Calibration for Convolutional Neural Networks Using Structured Dropout

arXiv: https://arxiv.org/abs/1906.09551 · HTML: https://mlsanity.com/paper/1906.09551/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2019.

## Built on by (most cited first, 19 of 19)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration](https://mlsanity.com/paper/2111.15430/) (2021)
- [DOCTOR: A Simple Method for Detecting Misclassification Errors](https://mlsanity.com/paper/2106.02395/) (2021)
- [Taxonomy of Machine Learning Safety: A Survey and Primer](https://mlsanity.com/paper/2106.04823/) (2021)
- [A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks](https://mlsanity.com/paper/2112.00337/) (2021)
- [Multiclass Confidence and Localization Calibration for Object Detection](https://mlsanity.com/paper/2306.08271/) (2023)
- [Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems](https://mlsanity.com/paper/2104.09286/) (2021)
- [Ex uno plures: Splitting One Model into an Ensemble of Subnetworks](https://mlsanity.com/paper/2106.04767/) (2021)
- [Navigating Beyond Dropout: An Intriguing Solution Towards Generalizable Image Super Resolution](https://mlsanity.com/paper/2402.18929/) (2024)
- [Marginally calibrated response distributions for end-to-end learning in autonomous driving](https://mlsanity.com/paper/2110.01050/) (2021)
- [Calibrating Segmentation Networks with Margin-based Label Smoothing](https://mlsanity.com/paper/2209.09641/) (2022)
- [Learning from Matured Dumb Teacher for Fine Generalization](https://mlsanity.com/paper/2108.05776/) (2021)
- [Uncertainty estimation in Deep Learning for Panoptic segmentation](https://mlsanity.com/paper/2304.02098/) (2023)
- [Perception and Semantic Aware Regularization for Sequential Confidence Calibration](https://mlsanity.com/paper/2305.19498/) (2023)
- [Multiclass Alignment of Confidence and Certainty for Network Calibration](https://mlsanity.com/paper/2309.02636/) (2023)
- [Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking](https://mlsanity.com/paper/2508.09116/) (2025)
- [Rethinking Soft Label in Label Distribution Learning Perspective](https://mlsanity.com/paper/2301.13444/) (2023)
- [Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA](https://mlsanity.com/paper/2406.16198/) (2024)
- [VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning](https://mlsanity.com/paper/2604.08639/) (2026)

## Abstract (arXiv)

In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked to Bayesian inference, yielding an efficient way to quantify uncertainty in neural network models. However, as previously demonstrated, confidence estimates computed with a naive implementation of dropout can be poorly calibrated, particularly when using convolutional networks. In this paper, through the lens of ensemble learning, we associate calibration error with the correlation between the models sampled with dropout. Motivated by this, we explore the use of structured dropout to promote model diversity and improve confidence calibration. We use the SVHN, CIFAR-10 and CIFAR-100 datasets to empirically compare model diversity and confidence errors obtained using various dropout techniques. We also show the merit of structured dropout in a Bayesian active learning application.