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

arXiv: https://arxiv.org/abs/1904.13196 · HTML: https://mlsanity.com/paper/1904.13196/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2019.

## Built on by (most cited first, 6 of 6)

- [From Statistical Relational to Neurosymbolic Artificial Intelligence: a Survey](https://mlsanity.com/paper/2108.11451/) (2021)
- [Multimodal Hate Speech Detection from Bengali Memes and Texts](https://mlsanity.com/paper/2204.10196/) (2022)
- [Neuro-Symbolic Learning: Principles and Applications in Ophthalmology](https://mlsanity.com/paper/2208.00374/) (2022)
- [PatchRefineNet: Improving Binary Segmentation by Incorporating Signals from Optimal Patch-wise Binarization](https://mlsanity.com/paper/2211.06560/) (2022)
- [Question Answering Over Biological Knowledge Graph via Amazon Alexa](https://mlsanity.com/paper/2210.06040/) (2022)
- [Neuro-Symbolic Spatio-Temporal Reasoning](https://mlsanity.com/paper/2211.15566/) (2022)

## Abstract (arXiv)

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.