# Confidence Estimation via Auxiliary Models

arXiv: https://arxiv.org/abs/2012.06508 · HTML: https://mlsanity.com/paper/2012.06508/

## Key facts

- Cited by 33 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 11 Dec 2020.

## Built on by (most cited first, 30 of 33)

- [Machine Learning with a Reject Option: A survey](https://mlsanity.com/paper/2107.11277/) (2021)
- [SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.08808/) (2022)
- [Explainability of deep vision-based autonomous driving systems: Review and challenges](https://mlsanity.com/paper/2101.05307/) (2021)
- [Rethinking Confidence Calibration for Failure Prediction](https://mlsanity.com/paper/2303.02970/) (2023)
- [OpenMix: Exploring Outlier Samples for Misclassification Detection](https://mlsanity.com/paper/2303.17093/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Spatio-Contextual Deep Network Based Multimodal Pedestrian Detection For Autonomous Driving](https://mlsanity.com/paper/2105.12713/) (2021)
- [SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation](https://mlsanity.com/paper/2304.03251/) (2023)
- [A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks](https://mlsanity.com/paper/2112.00337/) (2021)
- [How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networks](https://mlsanity.com/paper/2305.15508/) (2023)
- [Revisiting Confidence Estimation: Towards Reliable Failure Prediction](https://mlsanity.com/paper/2403.02886/) (2024)
- [Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models](https://mlsanity.com/paper/2505.05163/) (2025)
- [SURE: SUrvey REcipes for building reliable and robust deep networks](https://mlsanity.com/paper/2403.00543/) (2024)
- [Effective Pseudo-Labeling based on Heatmap for Unsupervised Domain Adaptation in Cell Detection](https://mlsanity.com/paper/2303.05269/) (2023)
- [Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization](https://mlsanity.com/paper/2311.02719/) (2023)
- [Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation](https://mlsanity.com/paper/2409.04409/) (2024)
- [ProtoGMM: Multi-prototype Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation](https://mlsanity.com/paper/2406.19225/) (2024)
- [Optimizing Calibration by Gaining Aware of Prediction Correctness](https://mlsanity.com/paper/2404.13016/) (2024)
- [Interpretable Out-Of-Distribution Detection Using Pattern Identification](https://mlsanity.com/paper/2302.10303/) (2023)
- [Perception and Semantic Aware Regularization for Sequential Confidence Calibration](https://mlsanity.com/paper/2305.19498/) (2023)
- [Bridging AI and Clinical Practice: Integrating Automated Sleep Scoring Algorithm with Uncertainty-Guided Physician Review](https://mlsanity.com/paper/2312.14996/) (2023)
- [Uncertainty Measurement of Deep Learning System based on the Convex Hull of Training Sets](https://mlsanity.com/paper/2405.16082/) (2024)
- [Explaining an image classifier with a generative model conditioned by uncertainty](https://mlsanity.com/paper/2410.13871/) (2024)
- [Localization Meets Uncertainty: Uncertainty-Aware Multi-Modal Localization](https://mlsanity.com/paper/2504.07677/) (2025)
- [On the Reliability and Stability of Selective Methods in Malware Classification Tasks](https://mlsanity.com/paper/2505.22843/) (2025)
- [Knowledge-driven Active Learning](https://mlsanity.com/paper/2110.08265/) (2021)
- [MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images](https://mlsanity.com/paper/2505.18741/) (2025)
- [A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts](https://mlsanity.com/paper/2511.11934/) (2025)
- [Integrating Knowledge Distillation Methods: A Sequential Multi-Stage Framework](https://mlsanity.com/paper/2601.15657/) (2026)
- [Trustworthy Endoscopic Super-Resolution](https://mlsanity.com/paper/2604.18001/) (2026)

## Abstract (arXiv)

Reliably quantifying the confidence of deep neural classifiers is a challenging yet fundamental requirement for deploying such models in safety-critical applications. In this paper, we introduce a novel target criterion for model confidence, namely the true class probability (TCP). We show that TCP offers better properties for confidence estimation than standard maximum class probability (MCP). Since the true class is by essence unknown at test time, we propose to learn TCP criterion from data with an auxiliary model, introducing a specific learning scheme adapted to this context. We evaluate our approach on the task of failure prediction and of self-training with pseudo-labels for domain adaptation, which both necessitate effective confidence estimates. Extensive experiments are conducted for validating the relevance of the proposed approach in each task. We study various network architectures and experiment with small and large datasets for image classification and semantic segmentation. In every tested benchmark, our approach outperforms strong baselines.