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

Research output: Contribution to journalArticleScientificpeer-review

Researchers

Research units

  • Örebro University

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.

Details

Original languageEnglish
Pages (from-to)863-880
Number of pages18
JournalSemantic Web
Volume10
Issue number5
Publication statusPublished - 2019
MoE publication typeA1 Journal article-refereed

    Research areas

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

ID: 37270880