Papers › Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation

Neural Network Meta Classifier: Improving the Reliability of Anomaly Segmentation

14 Dec 2024arXiv:2412.10765archive 2025-07-28

Jurica Runtas, Tomislav Petkovic

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.

PaperPDFCode

Code

juricaruntas/meta-ood officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Anomaly SegmentationSemantic Segmentationregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Logistic RegressionSET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections