A COMPARATIVE ANALYSIS OF UNSUPERVISED AND SEMI-SUPERVISED REPRESENTATION LEARNING FOR REMOTE SENSING IMAGE CATEGORIZATION

• Main Authors: P. J. Soto, J. D. Bermudez, P. N. Happ, R. Q. Feitosa
• Format: Article
• Language: English
• Published: Copernicus Publications 2019-09-01
• Series: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
• Online Access: https://www.isprs-ann-photogramm-remote-sens-spatial-inf-sci.net/IV-2-W7/167/2019/isprs-annals-IV-2-W7-167-2019.pdf

This work aims at investigating unsupervised and semi-supervised representation learning methods based on generative adversarial networks for remote sensing scene classification. The work introduces a novel approach, which consists in a semi-supervised extension of a prior unsupervised method, known as MARTA-GAN. The proposed approach was compared experimentally with two baselines upon two public datasets, <i>UC-MERCED</i> and <i>NWPU-RESISC45</i>. The experiments assessed the performance of each approach under different amounts of labeled data. The impact of fine-tuning was also investigated. The proposed method delivered in our analysis the best overall accuracy under scarce labeled samples, both in terms of absolute value and in terms of variability across multiple runs.