# Semantic Referee: A Neural-Symbolic Framework for Enhancing Geospatial Semantic Segmentation

## TL;DR

This paper introduces a neural-symbolic semantic referee that uses ontological reasoning to identify and correct errors in satellite image segmentation, improving model performance.

## Contribution

It presents a novel framework combining neural networks with ontological reasoning to enhance geospatial semantic segmentation accuracy.

## Key findings

- Improved segmentation accuracy on satellite imagery datasets.
- Effective error characterization through spatial ontological reasoning.
- Enhanced interaction between neural classifiers and semantic reasoners.

## Abstract

Understanding why machine learning algorithms may fail is usually the task of the human expert that uses domain knowledge and contextual information to discover systematic shortcomings in either the data or the algorithm. In this paper, we propose a semantic referee, which is able to extract qualitative features of the errors emerging from deep machine learning frameworks and suggest corrections. The semantic referee relies on ontological reasoning about spatial knowledge in order to characterize errors in terms of their spatial relations with the environment. Using semantics, the reasoner interacts with the learning algorithm as a supervisor. In this paper, the proposed method of the interaction between a neural network classifier and a semantic referee shows how to improve the performance of semantic segmentation for satellite imagery data.