Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation

Jurica Runtas, Tomislav Petković

2025

Abstract

Deep neural networks (DNNs) are a contemporary solution for semantic segmentation and are usually trained to operate on a predefined closed set of classes. In open-set environments, it is possible to encounter semantically unknown objects or anomalies. Road driving is an example of such an environment in which, from a safety standpoint, it is important to ensure that a DNN indicates it is operating outside of its learned semantic domain. One possible approach to anomaly segmentation is entropy maximization, which is paired with a logistic regression based post-processing step called meta classification, which is in turn used to improve the reliability of detection of anomalous pixels. We propose to substitute the logistic regression meta classifier with a more expressive lightweight fully connected neural network. We analyze advantages and drawbacks of the proposed neural network meta classifier and demonstrate its better performance over logistic regression. We also introduce the concept of informative out-of-distribution examples which we show to improve training results when using entropy maximization in practice. Finally, we discuss the loss of interpretability and show that the behavior of logistic regression and neural network is strongly correlated. The code is publicly available at https://github.com/JuricaRuntas/meta-ood.

Paper Citation

in Harvard Style

Runtas J. and Petković T. (2025). Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation. In Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-728-3, SciTePress, pages 348-355. DOI: 10.5220/0013143000003912

in Bibtex Style

@conference{visapp25,
author={Jurica Runtas and Tomislav Petković},
title={Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation},
booktitle={Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2025},
pages={348-355},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013143000003912},
isbn={978-989-758-728-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation
SN - 978-989-758-728-3
AU - Runtas J.
AU - Petković T.
PY - 2025
SP - 348
EP - 355
DO - 10.5220/0013143000003912
PB - SciTePress