English
Related papers

Related papers: How to Fix a Broken Confidence Estimator: Evaluati…

200 papers

There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and…

Machine Learning · Computer Science 2022-09-07 Xinshao Wang , Yang Hua , Elyor Kodirov , Sankha Subhra Mukherjee , David A. Clifton , Neil M. Robertson

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Antonio Loquercio , Mattia Segù , Davide Scaramuzza

Post-hoc calibration methods are widely used to improve the reliability of probabilistic predictions from machine learning models. Despite their prevalence, a comprehensive theoretical understanding of these methods remains elusive,…

Machine Learning · Computer Science 2025-09-30 Kristina P. Sinaga , Arjun S. Nair

Structured classification tasks such as sequence labeling and dependency parsing have seen much interest by the Natural Language Processing and the machine learning communities. Several online learning algorithms were adapted for structured…

Machine Learning · Computer Science 2011-11-08 Avihai Mejer , Koby Crammer

Hierarchical classification offers an approach to incorporate the concept of mistake severity by leveraging a structured, labeled hierarchy. However, decoding in such settings frequently relies on heuristic decision rules, which may not…

Machine Learning · Computer Science 2025-06-03 Roman Plaud , Alexandre Perez-Lebel , Matthieu Labeau , Antoine Saillenfest , Thomas Bonald

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 during training but face…

Machine Learning · Computer Science 2026-04-15 Sandra Gómez-Gálvez , Tobias Olenyi , Gillian Dobbie , Katerina Taškova

Deep learning models have significantly improved prediction accuracy in various fields, gaining recognition across numerous disciplines. Yet, an aspect of deep learning that remains insufficiently addressed is the assessment of prediction…

Machine Learning · Statistics 2024-12-18 Asaf Ben Arie , Malka Gorfine

Reliably quantifying the confidence of deep neural classifiers is a challenging yet fundamental requirement for deploying such models in safety-critical applications. In this paper, we introduce a novel target criterion for model…

Computer Vision and Pattern Recognition · Computer Science 2021-06-01 Charles Corbière , Nicolas Thome , Antoine Saporta , Tuan-Hung Vu , Matthieu Cord , Patrick Pérez

This paper develops a new approach to post-selection inference for screening high-dimensional predictors of survival outcomes. Post-selection inference for right-censored outcome data has been investigated in the literature, but much…

Methodology · Statistics 2021-12-22 Tzu-Jung Huang , Alex Luedtke , Ian W. McKeague

Since state-of-the-art uncertainty estimation methods are often computationally demanding, we investigate whether incorporating prior information can improve uncertainty estimates in conventional deep neural networks. Our focus is on…

Machine Learning · Computer Science 2025-03-21 Fabian Denoodt , José Oramas

Convolutional Neural Networks are a well-known staple of modern image classification. However, it can be difficult to assess the quality and robustness of such models. Deep models are known to perform well on a given training and estimation…

Machine Learning · Statistics 2018-02-06 Alexey Chaplygin , Joshua Chacksfield

Can we learn a binary classifier from only positive data, without any negative data or unlabeled data? We show that if one can equip positive data with confidence (positive-confidence), one can successfully learn a binary classifier, which…

Machine Learning · Statistics 2018-11-29 Takashi Ishida , Gang Niu , Masashi Sugiyama

Conformal predictors are an important class of algorithms that allow predictions to be made with a user-defined confidence level. They are able to do this by outputting prediction sets, rather than simple point predictions. The conformal…

Machine Learning · Computer Science 2021-05-25 Anthony Bellotti

Confidence estimation, a task that aims to evaluate the trustworthiness of the model's prediction output during deployment, has received lots of research attention recently, due to its importance for the safe deployment of deep models.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Haoxuan Qu , Yanchao Li , Lin Geng Foo , Jason Kuen , Jiuxiang Gu , Jun Liu

Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning rich feature extractors from large datasets. However, most deep learning…

Computer Vision and Pattern Recognition · Computer Science 2021-10-06 Xiaoyu Lin , Deblina Bhattacharjee , Majed El Helou , Sabine Süsstrunk

Generating confidence calibrated outputs is of utmost importance for the applications of deep neural networks in safety-critical decision-making systems. The output of a neural network is a probability distribution where the scores are…

Machine Learning · Computer Science 2021-09-17 Chihuang Liu , Joseph JaJa

Discriminatively trained, deterministic neural networks are the de facto choice for classification problems. However, even though they achieve state-of-the-art results on in-domain test sets, they tend to be overconfident on…

Machine Learning · Computer Science 2024-03-28 Ahmad Rashid , Serena Hacker , Guojun Zhang , Agustinus Kristiadi , Pascal Poupart

The problem of Voodoo correlations is recognized in neuroimaging as the problem of estimating quantities of interest from the same data that was used to select them as interesting. In statistical terminology, the problem of inference…

Methodology · Statistics 2014-12-11 Yoav Benjamini , Amit Meir

We derive inferential procedures for large sample sizes that remain valid under data-dependent significance levels (so-called "post-hoc valid inference"). Classical statistical tools require that the significance level -- the "type-I error"…

Statistics Theory · Mathematics 2026-03-10 Ben Chugg , Etienne Gauthier , Michael I. Jordan , Aaditya Ramdas , Ian Waudby-Smith

Post-hoc interpretability methods are critical tools to explain neural-network results. Several post-hoc methods have emerged in recent years, but when applied to a given task, they produce different results, raising the question of which…

Machine Learning · Computer Science 2024-12-09 Hugues Turbé , Mina Bjelogrlic , Christian Lovis , Gianmarco Mengaldo