Data to 14 Oct 2026

Addressing Failure Prediction by Learning Model Confidence

arXiv 1910.04851 ↗First posted 1 Oct 2019cs.CV cs.LG stat.MLcited by 186

Not on the map. Why?

Abstract (arXiv)

Assessing reliably the confidence of a deep neural network and predicting its failures is of primary importance for the practical deployment of these models. In this paper, we propose a new target criterion for model confidence, corresponding to the True Class Probability (TCP). We show how using the TCP is more suited than relying on the classic Maximum Class Probability (MCP). We provide in addition theoretical guarantees for TCP in the context of failure prediction. Since the true class is by essence unknown at test time, we propose to learn TCP criterion on the training set, introducing a specific learning scheme adapted to this context. Extensive experiments are conducted for validating the relevance of the proposed approach. We study various network architectures, small and large scale datasets for image classification and semantic segmentation. We show that our approach consistently outperforms several strong methods, from MCP to Bayesian uncertainty, as well as recent approaches specifically designed for failure prediction.

Key facts. Cited by 186 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 28; 2022: 30; 2023: 34; 2024: 35; 2025: 27; 2026: 32.

186 papers.

Sort:

By area:

2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 293
2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 256
2022TruFor: Leveraging all-round clues for trustworthy image forgery detection and localizationcited by 130
2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 95
2022Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectlycited by 89
2022RbA: Segmenting Unknown Regions Rejected by Allcited by 67
2021Optimal strategies for reject option classifierscited by 61
2021Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensemblescited by 54
2022A Call to Reflect on Evaluation Practices for Failure Detection in Image Classificationcited by 52
2021Trustworthy Long-Tailed Classificationcited by 51
2024Self-Consistency Preference Optimizationcited by 50
2024Multimodal Fusion on Low-quality Data: A Comprehensive Surveycited by 49

38 more

2023Rethinking Confidence Calibration for Failure Predictioncited by 43
2021Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentationcited by 40
2021Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributionscited by 39
2023OpenMix: Exploring Outlier Samples for Misclassification Detectioncited by 38
2024Overcoming Common Flaws in the Evaluation of Selective Classification Systemscited by 37
2022Augmenting Softmax Information for Selective Classification with Out-of-Distribution Datacited by 27
2023DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Modelscited by 26
2022Robust Models are less Over-Confidentcited by 25
2023Improving Selective Visual Question Answering by Learning from Your Peerscited by 25
2023Distribution Shift Inversion for Out-of-Distribution Predictioncited by 23
2022COLD Fusion: Calibrated and Ordinal Latent Distribution Fusion for Uncertainty-Aware Multimodal Emotion Recognitioncited by 22
2024Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertaintycited by 20
2021A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networkscited by 19
2021An evaluation of word-level confidence estimation for end-to-end automatic speech recognitioncited by 18
2022DIAL: Deep Interactive and Active Learning for Semantic Segmentation in Remote Sensingcited by 17
2022Latent Discriminant deterministic Uncertaintycited by 17
2023Calibrating Multimodal Learningcited by 17
2024Predictive Dynamic Fusioncited by 17
2021Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectorscited by 16
2021Distribution-Free Federated Learning with Conformal Predictionscited by 16
2022Human-AI Collaboration in Decision-Making: Beyond Learning to Defercited by 16
2023The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognitioncited by 16
2024Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generationcited by 16
2025PPGF: Probability Pattern-Guided Time Series Forecastingcited by 16
2021Anomaly Detection in Multi-Agent Trajectories for Automated Drivingcited by 15
2022Curved Geometric Networks for Visual Anomaly Recognitioncited by 15
2023ACLS: Adaptive and Conditional Label Smoothing for Network Calibrationcited by 15
2023OpenForest: A data catalogue for machine learning in forest monitoringcited by 15
2021Two Coupled Rejection Metrics Can Tell Adversarial Examples Apartcited by 14
2023A Data-Driven Measure of Relative Uncertainty for Misclassification Detectioncited by 14
2023Two Sides of Miscalibration: Identifying Over and Under-Confidence Prediction for Network Calibrationcited by 14
2025Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approachcited by 14
2021Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysiscited by 13
2021Detecting Anomalies in Semantic Segmentation with Prototypescited by 13
2021Empowering Language Understanding with Counterfactual Reasoningcited by 13
2022Uncertainty-aware Multi-modal Learning via Cross-modal Random Network Predictioncited by 13
2023Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognitioncited by 13
2024A Causal Framework for Evaluating Deferring Systemscited by 13

50 most cited of 186 All 186 (JSON)