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

Tracking #: 2152-3365

Authors: 
Marjan Alirezaie
Martin Längkvist
Michael Sioutis
Amy Loutfi

Responsible editor: 
Guest Editors Semantic Deep Learning 2018

Submission type: 
Full Paper
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.
Full PDF Version: 
Tags: 
Reviewed

Decision/Status: 
Accept

Solicited Reviews:
Click to Expand/Collapse
Review #1
By Dagmar Gromann submitted on 31/Mar/2019
Suggestion:
Accept
Review Comment:

We would like to cordially thank the authors for their tireless effort to accommodate reviewers' comments and all the considerable improvements they have made to their paper and are happy to welcome their publication to this special issue.