Home > Research > Publications & Outputs > A Self-Training Hierarchical Prototype-based En...

Electronic data

  • STHPensemble_final

    Rights statement: This is the author’s version of a work that was accepted for publication in Information Fusion. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Information Fusion, 80, 2021 DOI: 10.1016/j.inffus.2021.11.014

    Accepted author manuscript, 2.92 MB, PDF document

    Embargo ends: 18/05/23

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Links

Text available via DOI:

View graph of relations

A Self-Training Hierarchical Prototype-based Ensemble Framework for Remote Sensing Scene Classification

Research output: Contribution to journalJournal articlepeer-review

E-pub ahead of print
<mark>Journal publication date</mark>1/04/2022
<mark>Journal</mark>Information Fusion
Volume80
Number of pages26
Pages (from-to)179-204
Publication StatusE-pub ahead of print
Early online date18/11/21
<mark>Original language</mark>English

Abstract

Remote sensing scene classification plays a critical role in a wide range of real-world applications. Technically, however, scene classification is an extremely challenging task due to the huge complexity in remotely sensed scenes, and the difficulty in acquiring labelled data for model training such as supervised deep learning. To tackle these issues, a novel semi-supervised ensemble framework is proposed here using the self-training hierarchical prototype-based classifier as the base learner for chunk-by-chunk prediction. The framework has the ability to build a powerful ensemble model from both labelled and unlabelled images with minimum supervision. Different feature descriptors are employed in the proposed ensemble framework to offer multiple independent views of images. Thus, the diversity of base learners is guaranteed for ensemble classification. To further increase the overall accuracy, a novel cross-checking strategy was introduced to enable the base learners to exchange pseudo-labelling information during the self-training process, and maximize the correctness of pseudo-labels assigned to unlabelled images. Extensive numerical experiments on popular benchmark remote sensing scenes demonstrated the effectiveness of the proposed ensemble framework, especially where the number of labelled images available is limited. For example, the classification accuracy achieved on the OPTIMAL-31, PatternNet and RSI-CB256 datasets was up to 99.91%, 98. 67% and 99.07% with only 40% of the image sets used as labelled training images, surpassing or at least on par with mainstream benchmark approaches trained with double the number of labelled images.

Bibliographic note

This is the author’s version of a work that was accepted for publication in Information Fusion. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Information Fusion, 80, 2021 DOI: 10.1016/j.inffus.2021.11.014