In: Proceedings of the 3rd International Conference on Artificial Intelligence and Computer Vision (AICV2023), March 5–7, 2023. AICV 2023. Lecture Notes on Data Engineering and Communications Technologies, vol 164. Springer, Cham..
ISSN/ISBN: Not available at this time. DOI: 10.1007/978-3-031-27762-7_40
Abstract: Out-of-distribution data and anomalous inputs are vulnerabilities of machine learning systems today, often causing systems to make incorrect predictions. The diverse range of data on which these models are used makes detecting atypical inputs a difficult and important task. We assess a tool, Benford's law, as a method used to quantify the difference between real and corrupted inputs. We believe that in many settings, it could function as a filter for anomalous data points and for signalling out-of-distribution data. We hope to open a discussion on these applications and further areas where this technique is underexplored.
Bibtex:
@InProceedings{,
author="O'Mahony, Laura and O'Sullivan, David J.~P. and Nikolov, Nikola S.", editor="Hassanien, Aboul Ella and Haqiq, Abdelkrim and Azar, Ahmad Taher and Santosh, K.~C. and Jabbar, M.~A. and S{\l}owik, Adamand Subashini, Parthasarathy",
title="On the Detection of Anomalous or Out-of-Distribution Data in Vision Models Using Statistical Techniques",
booktitle="The 3rd International Conference on Artificial Intelligence and Computer Vision (AICV2023), March 5--7, 2023",
year="2023",
publisher="Springer Nature Switzerland",
address="Cham",
pages="426--435",
isbn="978-3-031-27762-7"
}
Reference Type: Conference Paper
Subject Area(s): Computer Science, Image Processing, Statistics