English
Related papers

Related papers: What Does Softmax Probability Tell Us about Classi…

200 papers

In recent years, deep neural networks have defined the state-of-the-art in semantic segmentation where their predictions are constrained to a predefined set of semantic classes. They are to be deployed in applications such as automated…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Kira Maag , Tobias Riedlinger

Existing works show that although modern neural networks achieve remarkable generalization performance on the in-distribution (ID) dataset, the accuracy drops significantly on the out-of-distribution (OOD) datasets \cite{recht2018cifar,…

Machine Learning · Computer Science 2022-03-30 Berfin Simsek , Melissa Hall , Levent Sagun

Meta-learning has demonstrated promising results in few-shot classification (FSC) by learning to solve new problems using prior knowledge. Bayesian methods are effective at characterizing uncertainty in FSC, which is crucial in high-risk…

Machine Learning · Computer Science 2024-10-14 Tianjun Ke , Haoqun Cao , Zenan Ling , Feng Zhou

Proper scoring rules are used to assess the out-of-sample accuracy of probabilistic forecasts, with different scoring rules rewarding distinct aspects of forecast performance. Herein, we re-investigate the practice of using proper scoring…

Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. Especially in autonomous systems, wrong predictions for OOD inputs can cause safety critical situations. As a first step…

Machine Learning · Computer Science 2020-04-17 Andreas Sedlmeier , Thomas Gabor , Thomy Phan , Lenz Belzner , Claudia Linnhoff-Popien

Uncertainty estimation is critical for cost-sensitive deep-learning applications (i.e. disease diagnosis). It is very challenging partly due to the inaccessibility of uncertainty groundtruth in most datasets. Previous works proposed to…

Machine Learning · Computer Science 2021-10-18 Bolian Li , Zige Zheng , Changqing Zhang

In many scientific tasks we are interested in discovering whether there exist any correlations in our data. This raises many questions, such as how to reliably and interpretably measure correlation between a multivariate set of attributes,…

Machine Learning · Computer Science 2019-09-02 Panagiotis Mandros , Mario Boley , Jilles Vreeken

With the widespread success of deep neural networks in science and technology, it is becoming increasingly important to quantify the uncertainty of the predictions produced by deep learning. In this paper, we introduce a new method that…

Machine Learning · Computer Science 2019-08-15 Qingyang Wu , He Li , Lexin Li , Zhou Yu

We address the problem of uncertainty quantification and propose measures of total, aleatoric, and epistemic uncertainty based on a known decomposition of (strictly) proper scoring rules, a specific type of loss function, into a divergence…

Machine Learning · Computer Science 2025-05-29 Paul Hofman , Yusuf Sale , Eyke Hüllermeier

Cross-entropy loss with softmax output is a standard choice to train neural network classifiers. We give a new view of neural network classifiers with softmax and cross-entropy as mutual information evaluators. We show that when the dataset…

Machine Learning · Computer Science 2021-08-17 Zhenyue Qin , Dongwoo Kim , Tom Gedeon

A probability forecast or probabilistic classifier is reliable or calibrated if the predicted probabilities are matched by ex post observed frequencies, as examined visually in reliability diagrams. The classical binning and counting…

Methodology · Statistics 2021-08-26 Timo Dimitriadis , Tilmann Gneiting , Alexander I. Jordan

Uncertainty representation and quantification are paramount in machine learning and constitute an important prerequisite for safety-critical applications. In this paper, we propose novel measures for the quantification of aleatoric and…

Machine Learning · Computer Science 2024-04-22 Paul Hofman , Yusuf Sale , Eyke Hüllermeier

PU learning refers to the classification problem in which only part of positive samples are labeled. Existing PU learning methods treat unlabeled samples equally. However, in many real tasks, from common sense or domain knowledge, some…

Machine Learning · Computer Science 2024-05-06 Puning Zhao , Jintao Deng , Xu Cheng

Self-training is a well-known approach for semi-supervised learning. It consists of iteratively assigning pseudo-labels to unlabeled data for which the model is confident and treating them as labeled examples. For neural networks, softmax…

Machine Learning · Computer Science 2024-04-04 Ambroise Odonnat , Vasilii Feofanov , Ievgen Redko

Learning with noisy labels can significantly hinder the generalization performance of deep neural networks (DNNs). Existing approaches address this issue through loss correction or example selection methods. However, these methods often…

Machine Learning · Computer Science 2024-06-05 Chen-Chen Zong , Ye-Wen Wang , Ming-Kun Xie , Sheng-Jun Huang

When deploying machine learning models in high-stakes real-world environments such as health care, it is crucial to accurately assess the uncertainty concerning a model's prediction on abnormal inputs. However, there is a scarcity of…

Machine Learning · Computer Science 2020-11-20 Dennis Ulmer , Lotta Meijerink , Giovanni Cinà

The application of machine learning in safety-critical systems requires a reliable assessment of uncertainty. However, deep neural networks are known to produce highly overconfident predictions on out-of-distribution (OOD) data. Even if…

Machine Learning · Computer Science 2022-10-19 Alexander Meinke , Julian Bitterwolf , Matthias Hein

Classifications organize entities into categories that identify similarities within a category and discern dissimilarities among categories, and they powerfully classify information in support of analysis. We propose a new classification…

Optimization and Control · Mathematics 2022-09-05 Casey Garner , Allen Holder

Class probabilities predicted by most multiclass classifiers are uncalibrated, often tending towards over-confidence. With neural networks, calibration can be improved by temperature scaling, a method to learn a single corrective…

Machine Learning · Computer Science 2019-10-29 Meelis Kull , Miquel Perello-Nieto , Markus Kängsepp , Telmo Silva Filho , Hao Song , Peter Flach

Building reliable classifiers is a fundamental challenge for deploying machine learning in real-world applications. A reliable system should not only detect out-of-distribution (OOD) inputs but also anticipate in-distribution (ID) errors by…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Yang Li , Youyang Sha , Yinzhi Wang , Timothy Hospedales , Xi Shen , Shell Xu Hu , Xuanlong Yu
‹ Prev 1 3 4 5 6 7 10 Next ›