English
Related papers

Related papers: Beyond temperature scaling: Obtaining well-calibra…

200 papers

Although deep neural networks (DNNs) achieve high predictive accuracy, their confidence estimates are often unreliable, potentially compromising user trust in their decisions. This has motivated research on calibrated models, where…

Machine Learning · Computer Science 2026-05-25 Ramya Hebbalaguppe , Ajay Shastry , Soumya Suvra Ghosal , Chetan Arora

Calibrating a multiclass predictor, that outputs a distribution over labels, is particularly challenging due to the exponential number of possible prediction values. In this work, we propose a new definition of calibration error that…

Machine Learning · Computer Science 2025-09-30 Konstantina Bairaktari , Huy L. Nguyen

Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanish. This paper…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Seyed Alireza Javid , Amirhossein Bagheri , Nuria González-Prelcic

The confidence calibration of deep learning-based perception models plays a crucial role in their reliability. Especially in the context of autonomous driving, downstream tasks like prediction and planning depend on accurate confidence…

Computer Vision and Pattern Recognition · Computer Science 2023-08-07 Mariella Dreissig , Florian Piewak , Joschka Boedecker

In many safety-critical applications such as autonomous driving and surgical robots, it is desirable to obtain prediction uncertainties from object detection modules to help support safe decision-making. Specifically, such modules need to…

Machine Learning · Computer Science 2018-11-29 Buu Phan , Rick Salay , Krzysztof Czarnecki , Vahdat Abdelzad , Taylor Denouden , Sachin Vernekar

Combining the outputs of multiple classifiers or experts into a single probabilistic classification is a fundamental task in machine learning with broad applications from classifier fusion to expert opinion pooling. Here we present a…

Machine Learning · Computer Science 2021-11-24 Susanne Trick , Constantin A. Rothkopf

We systematically study the calibration of classifiers trained with differentially private stochastic gradient descent (DP-SGD) and observe miscalibration across a wide range of vision and language tasks. Our analysis identifies per-example…

Machine Learning · Computer Science 2022-11-16 Hanlin Zhang , Xuechen Li , Prithviraj Sen , Salim Roukos , Tatsunori Hashimoto

Calibrating verbalized probabilities presents a novel approach for reliably assessing and leveraging outputs from black-box Large Language Models (LLMs). Recent methods have demonstrated improved calibration by applying techniques like…

Computation and Language · Computer Science 2024-10-10 Cheng Wang , Gyuri Szarvas , Georges Balazs , Pavel Danchenko , Patrick Ernst

Trustworthy classifiers are essential to the adoption of machine learning predictions in many real-world settings. The predicted probability of possible outcomes can inform high-stakes decision making, particularly when assessing the…

Machine Learning · Computer Science 2023-02-22 Kiri L. Wagstaff , Thomas G. Dietterich

Post-hoc multi-class calibration is a common approach for providing high-quality confidence estimates of deep neural network predictions. Recent work has shown that widely used scaling methods underestimate their calibration error, while…

Machine Learning · Computer Science 2022-11-28 Kanil Patel , William Beluch , Bin Yang , Michael Pfeiffer , Dan Zhang

We address the problem of uncertainty calibration and introduce a novel calibration method, Parametrized Temperature Scaling (PTS). Standard deep neural networks typically yield uncalibrated predictions, which can be transformed into…

Machine Learning · Computer Science 2022-09-20 Christian Tomani , Daniel Cremers , Florian Buettner

This paper explores the calibration of a classifier output score in binary classification problems. A calibrator is a function that maps the arbitrary classifier score, of a testing observation, onto $[0,1]$ to provide an estimate for the…

Machine Learning · Computer Science 2022-04-29 Waleed A. Yousef , Issa Traore , William Briguglio

Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {\em uncertainty}. Quantifying…

Deep neural networks with millions of parameters may suffer from poor generalization due to overfitting. To mitigate the issue, we propose a new regularization method that penalizes the predictive distribution between similar samples. In…

Machine Learning · Computer Science 2020-04-08 Sukmin Yun , Jongjin Park , Kimin Lee , Jinwoo Shin

Selective classification allows models to abstain from making predictions (e.g., say "I don't know") when in doubt in order to obtain better effective accuracy. While typical selective models can be effective at producing more accurate…

Machine Learning · Computer Science 2024-06-24 Adam Fisch , Tommi Jaakkola , Regina Barzilay

The consideration of predictive uncertainty in medical imaging with deep learning is of utmost importance. We apply estimation of both aleatoric and epistemic uncertainty by variational Bayesian inference with Monte Carlo dropout to…

Image and Video Processing · Electrical Eng. & Systems 2021-04-27 Max-Heinrich Laves , Sontje Ihler , Jacob F. Fast , Lüder A. Kahrs , Tobias Ortmaier

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The significance of calibration lies in its critical role in…

Audio and Speech Processing · Electrical Eng. & Systems 2024-06-27 Yaqian Hao , Chenguang Hu , Yingying Gao , Shilei Zhang , Junlan Feng

We propose a novel methodology for general multi-class classification in arbitrary feature spaces, which results in a potentially well-calibrated classifier. Calibrated classifiers are important in many applications because, in addition to…

Machine Learning · Statistics 2023-02-22 Raoul Heese , Jochen Schmid , Michał Walczak , Michael Bortz

Model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. The uncertainty does not represent the model error well. In this paper, temperature scaling is extended to dropout variational…

Machine Learning · Computer Science 2019-11-19 Max-Heinrich Laves , Sontje Ihler , Karl-Philipp Kortmann , Tobias Ortmaier

In typical machine learning systems, an estimate of the probability of the prediction is used to assess the system's confidence in the prediction. This confidence measure is usually uncalibrated; i.e.\ the system's confidence in the…

Computation and Language · Computer Science 2022-05-24 Shehzaad Dhuliawala , Leonard Adolphs , Rajarshi Das , Mrinmaya Sachan