中文
相关论文

相关论文: Consistency Calibration: Improving Uncertainty Cal…

200 篇论文

We address the problem of uncertainty calibration. While standard deep neural networks typically yield uncalibrated predictions, calibrated confidence scores that are representative of the true likelihood of a prediction can be achieved…

机器学习 · 计算机科学 2021-06-24 Christian Tomani , Sebastian Gruber , Muhammed Ebrar Erdem , Daniel Cremers , Florian Buettner

Despite extensive research on neural network calibration, existing methods typically apply global transformations that treat all predictions uniformly, overlooking the heterogeneous reliability of individual predictions. Furthermore, the…

机器学习 · 计算机科学 2025-10-22 Hassan Gharoun , Mohammad Sadegh Khorshidi , Kasra Ranjbarigderi , Fang Chen , Amir H. Gandomi

Reliable uncertainty estimation is critical for deploying neural networks (NNs) in real-world applications. While existing calibration techniques often rely on post-hoc adjustments or coarse-grained binning methods, they remain limited in…

机器学习 · 计算机科学 2025-05-30 Pedro Mendes , Paolo Romano , David Garlan

With model trustworthiness being crucial for sensitive real-world applications, practitioners are putting more and more focus on improving the uncertainty calibration of deep neural networks. Calibration errors are designed to quantify the…

机器学习 · 计算机科学 2024-03-14 Sebastian G. Gruber , Florian Buettner

Machine learning classifiers are probabilistic in nature, and thus inevitably involve uncertainty. Predicting the probability of a specific input to be correct is called uncertainty (or confidence) estimation and is crucial for risk…

机器学习 · 计算机科学 2023-01-11 Gabriella Chouraqui , Liron Cohen , Gil Einziger , Liel Leman

Calibrating deep neural models plays an important role in building reliable, robust AI systems in safety-critical applications. Recent work has shown that modern neural networks that possess high predictive capability are poorly calibrated…

机器学习 · 计算机科学 2025-09-16 Cheng Wang

Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…

机器学习 · 计算机科学 2023-08-08 Shuang Ao , Stefan Rueger , Advaith Siddharthan

Calibrating deep learning models to yield uncertainty-aware predictions is crucial as deep neural networks get increasingly deployed in safety-critical applications. While existing post-hoc calibration methods achieve impressive results on…

机器学习 · 计算机科学 2023-07-06 Christian Tomani , Futa Waseda , Yuesong Shen , Daniel Cremers

Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not…

机器学习 · 统计学 2019-11-01 Jayaraman J. Thiagarajan , Bindya Venkatesh , Deepta Rajan

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…

计算机视觉与模式识别 · 计算机科学 2020-09-10 Gongbo Liang , Yu Zhang , Xiaoqin Wang , Nathan Jacobs

This paper studies the problem of post-hoc calibration of machine learning classifiers. We introduce the following desiderata for uncertainty calibration: (a) accuracy-preserving, (b) data-efficient, and (c) high expressive power. We show…

机器学习 · 计算机科学 2020-07-01 Jize Zhang , Bhavya Kailkhura , T. Yong-Jin Han

Modern neural networks have found to be miscalibrated in terms of confidence calibration, i.e., their predicted confidence scores do not reflect the observed accuracy or precision. Recent work has introduced methods for post-hoc confidence…

计算机视觉与模式识别 · 计算机科学 2021-09-22 Fabian Küppers , Jan Kronenberger , Jonas Schneider , Anselm Haselhoff

Deep neural networks (DNNs) have achieved significant success across various tasks, but ensuring reliable uncertainty estimates, known as model calibration, is crucial for their safe and effective deployment. Modern DNNs often suffer from…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Linwei Tao , Minjing Dong , Chang Xu

Optimal decision making requires that classifiers produce uncertainty estimates consistent with their empirical accuracy. However, deep neural networks are often under- or over-confident in their predictions. Consequently, methods have been…

Deep Neural Networks (DNNs), despite their tremendous success in recent years, could still cast doubts on their predictions due to the intrinsic uncertainty associated with their learning process. Ensemble techniques and post-hoc…

机器学习 · 计算机科学 2022-03-03 Chunwei Ma , Ziyun Huang , Jiayi Xian , Mingchen Gao , Jinhui Xu

Predicting calibrated confidence scores for multi-class deep networks is important for avoiding rare but costly mistakes. A common approach is to learn a post-hoc calibration function that transforms the output of the original network into…

机器学习 · 计算机科学 2020-10-26 Amir Rahimi , Amirreza Shaban , Ching-An Cheng , Richard Hartley , Byron Boots

Deep neural networks often produce miscalibrated probability estimates, leading to overconfident predictions. A common approach for calibration is fitting a post-hoc calibration map on unseen validation data that transforms predicted…

机器学习 · 计算机科学 2025-07-10 Yunrui Zhang , Gustavo Batista , Salil S. Kanhere

Uncertainty calibration is crucial for various machine learning applications, yet it remains challenging. Many models exhibit hallucinations - confident yet inaccurate responses - due to miscalibrated confidence. Here, we show that the…

机器学习 · 计算机科学 2025-03-28 Jeonghwan Cheon , Se-Bum Paik

Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data. Unfortunately, CL models tend to forget previous knowledge, thus often underperforming when compared with an offline…

机器学习 · 计算机科学 2024-04-15 Lanpei Li , Elia Piccoli , Andrea Cossu , Davide Bacciu , Vincenzo Lomonaco

Despite their incredible performance, it is well reported that deep neural networks tend to be overoptimistic about their prediction confidence. Finding effective and efficient calibration methods for neural networks is therefore an…

机器学习 · 计算机科学 2023-09-07 Lucas Clarté , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová
‹ 上一页 1 2 3 10 下一页 ›