mlsanityData to 7 Oct 2026

Uncertainty Sets for Image Classifiers using Conformal Prediction

arXiv 2009.14193 ↗First posted 29 Sep 2020cs.CV math.ST stat.MLcited by 365

Not on the map. Why?

Abstract (arXiv)

Convolutional image classifiers can achieve high predictive accuracy, but quantifying their uncertainty remains an unresolved challenge, hindering their deployment in consequential settings. Existing uncertainty quantification techniques, such as Platt scaling, attempt to calibrate the network's probability estimates, but they do not have formal guarantees. We present an algorithm that modifies any classifier to output a predictive set containing the true label with a user-specified probability, such as 90%. The algorithm is simple and fast like Platt scaling, but provides a formal finite-sample coverage guarantee for every model and dataset. Our method modifies an existing conformal prediction algorithm to give more stable predictive sets by regularizing the small scores of unlikely classes after Platt scaling. In experiments on both Imagenet and Imagenet-V2 with ResNet-152 and other classifiers, our scheme outperforms existing approaches, achieving coverage with sets that are often factors of 5 to 10 smaller than a stand-alone Platt scaling baseline.

Key facts. Cited by 365 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Sep 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 43; 2023: 51; 2024: 87; 2025: 95; 2026: 65.

365 papers.

Sort:

By area:

  1. 2021A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantificationcited by 777
  2. 2023Robots That Ask For Help: Uncertainty Alignment for Large Language Model Plannerscited by 298
  3. 2022Conformal Risk Controlcited by 290
  4. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  5. 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 256
  6. 2023Conformal Language Modelingcited by 163
  7. 2021Testing for Outliers with Conformal p-valuescited by 133
  8. 2023Conformal Prediction with Large Language Models for Multi-Choice Question Answeringcited by 131
  9. 2024Benchmarking LLMs via Uncertainty Quantificationcited by 124
  10. 2023Class-Conditional Conformal Prediction with Many Classescited by 109
  11. 2021Learning Optimal Conformal Classifierscited by 108
  12. 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
38 more
  1. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  2. 2021Distribution-free uncertainty quantification for classification under label shiftcited by 99
  3. 2022Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectlycited by 86
  4. 2023Uncertainty Quantification over Graph with Conformalized Graph Neural Networkscited by 79
  5. 2023Improved Online Conformal Prediction via Strongly Adaptive Online Learningcited by 76
  6. 2021Fair Conformal Predictors for Applications in Medical Imagingcited by 74
  7. 2022Sequential Predictive Conformal Inference for Time Seriescited by 71
  8. 2024API Is Enough: Conformal Prediction for Large Language Models Without Logit-Accesscited by 68
  9. 2022Batch Multivalid Conformal Predictioncited by 66
  10. 2022Practical Adversarial Multivalid Conformal Predictioncited by 65
  11. 2022Training Uncertainty-Aware Classifiers with Conformalized Deep Learningcited by 62
  12. 2022Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysiscited by 62
  13. 2022Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensemblescited by 59
  14. 2022Improving Expert Predictions with Conformal Predictioncited by 54
  15. 2021Few-shot Conformal Prediction with Auxiliary Taskscited by 53
  16. 2023Conformal Prediction for Deep Classifier via Label Rankingcited by 52
  17. 2021Improving Conditional Coverage via Orthogonal Quantile Regressioncited by 48
  18. 2023Federated Conformal Predictors for Distributed Uncertainty Quantificationcited by 46
  19. 2021Sample-Efficient Safety Assurances using Conformal Predictioncited by 41
  20. 2023High-Dimensional Prediction for Sequential Decision Makingcited by 41
  21. 2023Conformal Prediction for Time Series with Modern Hopfield Networkscited by 40
  22. 2022Achieving Risk Control in Online Learning Settingscited by 38
  23. 2022Improving Trustworthiness of AI Disease Severity Rating in Medical Imaging with Ordinal Conformal Prediction Setscited by 38
  24. 2024Conformal prediction for multi-dimensional time series by ellipsoidal setscited by 37
  25. 2025Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agentscited by 37
  26. 2024Conformal Prediction Sets Improve Human Decision Makingcited by 35
  27. 2022On the Utility of Prediction Sets in Human-AI Teamscited by 34
  28. 2022Predictive Inference with Feature Conformal Predictioncited by 33
  29. 2023Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagationcited by 33
  30. 2023Conformal prediction under ambiguous ground truthcited by 31
  31. 2023Conformal Prediction for Federated Uncertainty Quantification Under Label Shiftcited by 29
  32. 2022Conformal Prediction Sets with Limited False Positivescited by 28
  33. 2022Distribution Free Prediction Sets for Node Classificationcited by 28
  34. 2024Provably Robust Conformal Prediction with Improved Efficiencycited by 27
  35. 2025Analyzing Uncertainty of LLM-as-a-Judge: Interval Evaluations with Conformal Predictioncited by 26
  36. 2022Efficient and Differentiable Conformal Prediction with General Function Classescited by 25
  37. 2022Conformal Prediction with Temporal Quantile Adjustmentscited by 25
  38. 2023Beyond Confidence: Reliable Models Should Also Consider Atypicalitycited by 25

50 most cited of 365 All 365 (JSON)