Robustness and uncertainty: two complementary aspects of the reliability of the predictions of a classifier
Not on the map. Why?
Abstract (arXiv)
We consider two conceptually different approaches for assessing the reliability of the individual predictions of a classifier: Robustness Quantification (RQ) and Uncertainty Quantification (UQ). We compare both approaches on a number of benchmark datasets and show that there is no clear winner between the two, but that they are complementary and can be combined to obtain a hybrid approach that outperforms both RQ and UQ. As a byproduct of our approach, for each dataset, we also obtain an assessment of the relative importance of uncertainty and robustness as sources of unreliability.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 7 of its 16 references that are in the map. First posted on arXiv 17 Dec 2025.
Builds on
7 of 16 references.
References · 7
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
- 2020Measuring Robustness to Natural Distribution Shifts in Image Classificationcited by 454
- 2019On Evaluating Adversarial Robustnesscited by 447
- 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
- 2020Aleatoric and Epistemic Uncertainty with Random Forestscited by 43
- 2020Towards Robust Classification with Deep Generative Forestscited by 5
- 2025Robustness quantification: a new method for assessing the reliability of the predictions of a classifiercited by 4
Built on by
Citing papers per year: 2026: 2.
2 papers.