Guidelines for the selection, calibration, and evaluation of post-hoc OOD detectors in high-dimensional representations generated by CNN and ViT models in image recognition
Open Access
- 26 March 2026
- journal article
- Published by Elsevier in Expert Systems with Applications
- Vol. 321
Abstract
No abstract availableThis publication has 12 references indexed in Scilit:
- Managing extreme AI risks amid rapid progressScience, 2024
- Rethinking Out-of-Distribution Detection From a Human-Centric PerspectiveInternational Journal of Computer Vision, 2024
- Effective Out-of-Distribution Detection in Classifier Based on PEDCC-LossNeural Processing Letters, 2022
- Evaluating pointwise reliability of machine learning predictionJournal of Biomedical Informatics, 2022
- ADBench: Anomaly Detection Benchmark2022
- SciPy 1.0: fundamental algorithms for scientific computing in PythonNature Methods, 2020
- Integrated rank-weighted depthJournal of Multivariate Analysis, 2019
- Places: A 10 Million Image Database for Scene RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2017
- An experimental evaluation of novelty detection methodsNeurocomputing, 2014
- Anomaly detectionACM Computing Surveys, 2009