Methods for non-intrusive out-of-distribution images detection

Anastasiia V. Vlasova; Aleksandr Yu. Shkanaev; Dmitry L. Sholomov

doi:10.1117/12.3023403

3 April 2024 Methods for non-intrusive out-of-distribution images detection

Anastasiia V. Vlasova, Aleksandr Yu. Shkanaev, Dmitry L. Sholomov

Proceedings Volume 13072, Sixteenth International Conference on Machine Vision (ICMV 2023); 130720N (2024) https://doi.org/10.1117/12.3023403
Event: Sixteenth International Conference on Machine Vision (ICMV 2023), 2023, Yerevan, Armenia

Abstract

Selecting representative data is a key factor in improving the performance of machine learning algorithms. In this paper we focus on out-of-distribution (OoD) methods evaluation, which can be integrated into ML project lifecycle in a nonintrusive way, without changing a model architecture. Considered methods are applicable to image classification datasets analysis. In addition to commonly used AUROC metric, we evaluate the number of out-of-distribution samples misclassified with high confidence. Case studies were conducted on benchmark and production datasets. As a result, we provide practical guidance for data evaluation and recommendations on which method to use to detect different types of OoD images.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Anastasiia V. Vlasova, Aleksandr Yu. Shkanaev, and Dmitry L. Sholomov "Methods for non-intrusive out-of-distribution images detection", Proc. SPIE 13072, Sixteenth International Conference on Machine Vision (ICMV 2023), 130720N (3 April 2024); https://doi.org/10.1117/12.3023403

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available