paper-with-me

Papers

Calibration tests in multi-class classification: A unifying framework

2019-10-24 · NeurIPS 2019 12 · David Widmann, Fredrik Lindsten, Dave Zachariah

In safety-critical applications a probabilistic model is usually required to be calibrated, i.e., to capture the uncertainty of its predictions accurately. In multi-class classification, calibration of the most confident predictions only is often not sufficient. We propose and study calibration measures for multi-class classification that generalize existing measures such as the expected calibration error, the maximum calibration error, and the maximum mean calibration error. We propose and evaluate empirically different consistent and unbiased estimators for a specific class of measures based on matrix-valued kernels. Importantly, these estimators can be interpreted as test statistics associated with well-defined bounds and approximations of the p-value under the null hypothesis that the model is calibrated, significantly improving the interpretability of calibration measures, which otherwise lack any meaningful unit or scale.

📄 PDF Abstract BibTeX arXiv:1910.11385

Code (1)

devmotion/CalibrationPaper 공식 구현

Tasks

ClassificationGeneral ClassificationMulti-class Classification

Methods 이 논문이 사용한 방법론

Test 설명 없음
Interpretability 설명 없음

Similar Papers 제목 키워드 기반

Calibration tests beyond classification

2022-10-21 · ICLR 2021 1 · David Widmann, Fredrik Lindsten, Dave Zachariah

Most supervised machine learning tasks are subject to irreducible prediction errors. Probabilistic predictive models address this limitation by providing probability distributions that represent a belief over plausible t…

ClassificationDecision MakingDecision Making Under UncertaintyMulti-class Classification+1

Socrates Loss: Unifying Confidence Calibration and Classification by Leveraging the Unknown

2026-04-14 · Sandra Gómez-Gálvez, Tobias Olenyi, Gillian Dobbie, Katerina Taškova arxiv

Deep neural networks, despite their high accuracy, often exhibit poor confidence calibration, limiting their reliability in high-stakes applications. Current ad-hoc confidence calibration methods attempt to fix this duri…

A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning

2023-02-21 · NeurIPS 2023 11

We provide a unifying framework for the design and analysis of multicalibrated predictors. By placing the multicalibration problem in the general setting of multi-objective learning -- where learning guarantees must hold…

Fairness

On Calibrating Semantic Segmentation Models: Analyses and An Algorithm

2022-12-22 · CVPR 2023 1 · Dongdong Wang, Boqing Gong, Liqiang Wang

We study the problem of semantic segmentation calibration. Lots of solutions have been proposed to approach model miscalibration of confidence in image classification. However, to date, confidence calibration research on…

image-classificationImage ClassificationPredictionSegmentation+1

Calibrated and uncertain? Evaluating uncertainty estimates in binary classification models

2025-08-15 · Aurora Grefsrud, Nello Blaser, Trygve Buanes arxiv

Rigorous statistical methods, including parameter estimation with accompanying uncertainties, underpin the validity of scientific discovery, especially in the natural sciences. With increasingly complex data models such …

Binary ClassificationBayesian Inference