mlsanityData to 7 Oct 2026

Calibrate to Interpret

arXiv 2207.03324 ↗First posted 7 Jul 2022cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness, explainability and formal guaranties. Each of these individual domains gains the ML community interest, visible by the number of related publications. However few works tackle the interconnection between these fields. In this paper we show a first link between uncertainty and explainability, by studying the relation between calibration and interpretation. As the calibration of a given model changes the way it scores samples, and interpretation approaches often rely on these scores, it seems safe to assume that the confidence-calibration of a model interacts with our ability to interpret such model. In this paper, we show, in the context of networks trained on image classification tasks, to what extent interpretations are sensitive to confidence-calibration. It leads us to suggest a simple practice to improve the interpretation outcomes: Calibrate to Interpret.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 47 references that are in the map. First posted on arXiv 7 Jul 2022.

Builds on

31 of 47 references.

References · 31

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  8. 2018Sanity Checks for Saliency Mapscited by 1,149
  9. 2017SmoothGrad: removing noise by adding noisecited by 1,097
  10. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  11. 2018Robustness May Be at Odds with Accuracycited by 873
  12. 2018RISE: Randomized Input Sampling for Explanation of Black-box Modelscited by 825
19 more
  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  2. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  3. 2017Interpretable Explanations of Black Boxes by Meaningful Perturbationcited by 611
  4. 2020Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?cited by 590
  5. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 575
  6. 2020Estimating Training Data Influence by Tracing Gradient Descentcited by 565
  7. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  8. 2017Interpretation of Neural Networks is Fragilecited by 443
  9. 2017On Fairness and Calibrationcited by 406
  10. 2019Beyond temperature scaling: Obtaining well-calibrated multiclass probabilities with Dirichlet calibrationcited by 359
  11. 2017The (Un)reliability of saliency methodscited by 331
  12. 2018On the Robustness of Interpretability Methodscited by 310
  13. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  14. 2020Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixupcited by 260
  15. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  16. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  17. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  18. 2021Estimating Expected Calibration Errorscited by 24
  19. 2019Model Explanations under Calibrationcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 2.

3 papers.

  1. 2023Understanding Calibration of Deep Neural Networks for Medical Image Classificationcited by 5
  2. 2025Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibrationcited by 2
  3. 2025Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanationscited by 0