Scale Aware Adaptation for Land-Cover Classification in Remote Sensing Imagery

TL;DR

This paper introduces a scale-aware adversarial learning framework with a dual discriminator and scale attention module to improve land-cover classification across different locations and scales in remote sensing imagery.

Contribution

It proposes a novel scale-aware adversarial framework with a dual discriminator and scale attention module for better cross-scale and cross-location land-cover classification.

Findings

Outperforms state-of-the-art domain adaptation methods significantly

Effective handling of scale variation in remote sensing imagery

Improves generalization across different datasets and scales

Abstract

Land-cover classification using remote sensing imagery is an important Earth observation task. Recently, land cover classification has benefited from the development of fully connected neural networks for semantic segmentation. The benchmark datasets available for training deep segmentation models in remote sensing imagery tend to be small, however, often consisting of only a handful of images from a single location with a single scale. This limits the models' ability to generalize to other datasets. Domain adaptation has been proposed to improve the models' generalization but we find these approaches are not effective for dealing with the scale variation commonly found between remote sensing image collections. We therefore propose a scale aware adversarial learning framework to perform joint cross-location and cross-scale land-cover classification. The framework has a dual discriminator architecture with a standard feature discriminator as well as a novel scale discriminator. We also introduce a scale attention module which produces scale-enhanced features. Experimental results show that the proposed framework outperforms state-of-the-art domain adaptation methods by a large margin.