mlsanityData to 7 Oct 2026

Improving the Reliability for Confidence Estimation

arXiv 2210.06776 ↗First posted 13 Oct 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Confidence estimation, a task that aims to evaluate the trustworthiness of the model's prediction output during deployment, has received lots of research attention recently, due to its importance for the safe deployment of deep models. Previous works have outlined two important qualities that a reliable confidence estimation model should possess, i.e., the ability to perform well under label imbalance and the ability to handle various out-of-distribution data inputs. In this work, we propose a meta-learning framework that can simultaneously improve upon both qualities in a confidence estimation model. Specifically, we first construct virtual training and testing sets with some intentionally designed distribution differences between them. Our framework then uses the constructed sets to train the confidence estimation model through a virtual training and testing scheme leading it to learn knowledge that generalizes to diverse distributions. We show the effectiveness of our framework on both monocular depth estimation and image classification.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

36 of 52 references.

References · 36

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  8. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  9. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  10. 2016Concrete Problems in AI Safetycited by 1,582
  11. 2020Sharpness-Aware Minimization for Efficiently Improving Generalizationcited by 1,404
  12. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
24 more
  1. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
  2. 2019From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimationcited by 379
  3. 2020Calibrating Deep Neural Networks using Focal Losscited by 353
  4. 2017Sparsity Invariant CNNscited by 325
  5. 2021Gradient Matching for Domain Generalizationcited by 258
  6. 2018Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shiftcited by 240
  7. 2018To Trust Or Not To Trust A Classifiercited by 205
  8. 2019Addressing Failure Prediction by Learning Model Confidencecited by 183
  9. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  10. 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
  11. 2020Confidence-Aware Learning for Deep Neural Networkscited by 113
  12. 2018Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understandingcited by 98
  13. 2020On Feature Normalization and Data Augmentationcited by 71
  14. 2020Learning Meta Face Recognition in Unseen Domainscited by 61
  15. 2020Post-hoc Uncertainty Calibration for Domain Drift Scenarioscited by 61
  16. 2021Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensemblescited by 54
  17. 2022MetaSets: Meta-Learning on Point Sets for Generalizable Representationscited by 22
  18. 2022Meta Spatio-Temporal Debiasing for Video Scene Graph Generationcited by 20
  19. 2021SLURP: Side Learning Uncertainty for Regression Problemscited by 12
  20. 2021Learning to Predict Trustworthiness with Steep Slope Losscited by 11
  21. 2017Influence of Resampling on Accuracy of Imbalanced Classificationcited by 8
  22. 2020Detecting Misclassification Errors in Neural Networks with a Gaussian Process Modelcited by 8
  23. 2020Failure Prediction by Confidence Estimation of Uncertainty-Aware Dirichlet Networkscited by 3
  24. 2021Identifying Incorrect Classifications with Balanced Uncertaintycited by 1

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1; 2025: 2.

6 papers.

  1. 2023LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognitioncited by 10
  2. 2023Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regressioncited by 7
  3. 2024DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanationcited by 6
  4. 2023Measuring and Modeling Uncertainty Degree for Monocular Depth Estimationcited by 1
  5. 2025TRUST: Test-time Resource Utilization for Superior Trustworthinesscited by 0
  6. 2025Continual Error Correction on Low-Resource Devicescited by 0