Increasing the effectiveness of active learning: Introducing artificial data generation in active learning for land use/land cover classification

Research output: Contribution to journalArticlepeer-review

Abstract

In remote sensing, Active Learning (AL) has become an important technique to collect informative ground truth data “on-demand” for supervised classification tasks. Despite its effectiveness, it is still significantly reliant on user interaction, which makes it both expensive and time consuming to implement. Most of the current literature focuses on the optimization of AL by modifying the selection criteria and the classifiers used. Although improvements in these areas will result in more effective data collection, the use of artificial data sources to reduce human–computer interaction remains unexplored. In this paper, we introduce a new component to the typical AL framework, the data generator, a source of artificial data to reduce the amount of user-labeled data required in AL. The implementation of the proposed AL framework is done using Geometric SMOTE as the data generator. We compare the new AL framework to the original one using similar acquisition functions and classifiers over three AL-specific performance metrics in seven benchmark datasets. We show that this modification of the AL framework significantly reduces cost and time requirements for a successful AL implementation in all of the datasets used in the experiment.

Original languageEnglish
Article number2619
Pages (from-to)1-20
Number of pages20
JournalRemote Sensing
Volume13
Issue number13
DOIs
Publication statusPublished - 1 Jul 2021

Keywords

  • Active learning
  • Artificial data generation
  • Land use/land cover classification
  • Oversampling
  • SMOTE

Fingerprint

Dive into the research topics of 'Increasing the effectiveness of active learning: Introducing artificial data generation in active learning for land use/land cover classification'. Together they form a unique fingerprint.

Cite this