Home > Research > Publications & Outputs > A Semi-Supervised Deep Rule-Based Approach for ...

Electronic data

  • INNSBDDL34

    Accepted author manuscript, 786 KB, PDF document

Links

Text available via DOI:

View graph of relations

A Semi-Supervised Deep Rule-Based Approach for Remote Sensing Scene Classication

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paper

Published
Publication date3/04/2019
Host publicationThe 2019 INNS Big Data and Deep Learning (INNSBDDL 2019) conference
PublisherSpringer
Pages257-266
Number of pages10
ISBN (Electronic)9783030168414
ISBN (Print)9783030168407
Original languageEnglish
EventINNS Conference on Big Data and Deep Learning -
Duration: 16/04/2019 → …
https://innsbddl2019.org/

Conference

ConferenceINNS Conference on Big Data and Deep Learning
Period16/04/19 → …
Internet address

Conference

ConferenceINNS Conference on Big Data and Deep Learning
Period16/04/19 → …
Internet address

Abstract

This paper proposes a new approach that is based on the recently introduced semi-supervised deep rule-based classifier for remote sensing scene classification. The proposed approach employs a pre-trained deep convoluational neural network as the feature descriptor to extract high-level discriminative semantic features from the sub-regions of the remote sensing images. This approach is able to self-organize a set of prototype-based IF...THEN rules from few labeled training images through an efficient supervised initialization process, and continuously self-updates the rule base with the unlabeled images in an unsupervised, autonomous, transparent and human-interpretable manner. Highly accurate classification on the unlabeled images is performed at the end of the learning process. Numerical examples demonstrate that the proposed approach is a strong alternative to the state-of-the-art ones.