paper-with-me

홈 › Papers

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

2023-06-02 · Eduardo Dadalto, Marco Romanelli, Georg Pichler, Pablo Piantanida

Misclassification detection is an important problem in machine learning, as it allows for the identification of instances where the model's predictions are unreliable. However, conventional uncertainty measures such as Shannon entropy do not provide an effective way to infer the real uncertainty associated with the model's predictions. In this paper, we introduce a novel data-driven measure of uncertainty relative to an observer for misclassification detection. By learning patterns in the distribution of soft-predictions, our uncertainty measure can identify misclassified samples based on the predicted class probabilities. Interestingly, according to the proposed measure, soft-predictions corresponding to misclassified instances can carry a large amount of uncertainty, even though they may have low Shannon entropy. We demonstrate empirical improvements over multiple image classification tasks, outperforming state-of-the-art misclassification detection methods.

📄 PDF Abstract BibTeX arXiv:2306.01710

Code (1)

edadaltocg/relative-uncertainty 공식 구현 pytorch

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Ensembling Uncertainty Measures to Improve Safety of Black-Box Classifiers

2023-08-23 · Tommaso Zoppi, Andrea Ceccarelli, Andrea Bondavalli

Machine Learning (ML) algorithms that perform classification may predict the wrong class, experiencing misclassifications. It is well-known that misclassifications may have cascading effects on the encompassing system, p…

Multi-class Classification

Enhancing Decision-Making in Windows PE Malware Classification During Dataset Shifts with Uncertainty Estimation

2025-12-20 · Rahul Yumlembam, Biju Issac, Seibu Mary Jacob arxiv

Artificial intelligence techniques have achieved strong performance in classifying Windows Portable Executable (PE) malware, but their reliability often degrades under dataset shifts, leading to misclassifications with s…

Malware Classification

The Limitations of Model Uncertainty in Adversarial Settings

2018-12-06 · Kathrin Grosse, David Pfaff, Michael Thomas Smith, Michael Backes

Machine learning models are vulnerable to adversarial examples: minor perturbations to input samples intended to deliberately cause misclassification. While an obvious security threat, adversarial examples yield as well …

BIG-bench Machine LearningGaussian Processesmodel

On Information-Theoretic Measures of Predictive Uncertainty

2024-10-14 · Kajetan Schweighofer, Lukas Aichberger, Mykyta Ielanskyi, Sepp Hochreiter

Reliable estimation of predictive uncertainty is crucial for machine learning applications, particularly in high-stakes scenarios where hedging against risks is essential. Despite its significance, a consensus on the cor…

Out-of-Distribution Detection

The VOROS: Lifting ROC curves to 3D

2024-02-28 · Christopher Ratigan, Lenore Cowen

While the area under the ROC curve is perhaps the most common measure that is used to rank the relative performance of different binary classifiers, longstanding field folklore has noted that it can be a measure that ill…