Semantic referee: A neural-symbolic framework for enhancing geospatial semantic segmentation

Loading...
Thumbnail Image

Access rights

openAccess
acceptedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2019

Major/Subject

Mcode

Degree programme

Language

en

Pages

18

Series

Semantic Web, Volume 10, issue 5, pp. 863-880

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.

Description

Keywords

Deep neural network, geo data, ontocity, ontological and spatial reasoning, semantic referee, semantic segmentation

Other note

Citation

Alirezaie, M, Längkvist, M, Sioutis, M & Loutfi, A 2019, ' Semantic referee : A neural-symbolic framework for enhancing geospatial semantic segmentation ', Semantic Web, vol. 10, no. 5, pp. 863-880 . https://doi.org/10.3233/SW-180362