State-of-the-art and gaps for deep learning on limited training data in remote sensing

TL;DR

This paper reviews advanced deep learning methods like transfer learning, unsupervised learning, and GANs to address the challenge of limited labeled data in remote sensing applications.

Contribution

It provides a comprehensive overview of current approaches and identifies gaps in deep learning techniques for remote sensing with limited training data.

Findings

Transfer learning improves model performance with limited data.

Unsupervised learning leverages unlabeled data effectively.

GANs generate realistic data to augment training sets.

Abstract

Deep learning usually requires big data, with respect to both volume and variety. However, most remote sensing applications only have limited training data, of which a small subset is labeled. Herein, we review three state-of-the-art approaches in deep learning to combat this challenge. The first topic is transfer learning, in which some aspects of one domain, e.g., features, are transferred to another domain. The next is unsupervised learning, e.g., autoencoders, which operate on unlabeled data. The last is generative adversarial networks, which can generate realistic looking data that can fool the likes of both a deep learning network and human. The aim of this article is to raise awareness of this dilemma, to direct the reader to existing work and to highlight current gaps that need solving.