Semantic Segmentation of Medium-Resolution Satellite Imagery using Conditional Generative Adversarial Networks
This work offers an incremental improvement in land cover classification for practitioners working with medium-resolution satellite imagery, particularly in scenarios with diverse landscapes and limited labels.
This paper addresses the challenge of semantic segmentation in medium-resolution satellite imagery, where traditional CNNs struggle with generalization due to data diversity and label scarcity. The authors propose a Conditional Generative Adversarial Network (CGAN) framework, which significantly outperforms a CNN of similar complexity on an unseen, imbalanced test dataset.
Semantic segmentation of satellite imagery is a common approach to identify patterns and detect changes around the planet. Most of the state-of-the-art semantic segmentation models are trained in a fully supervised way using Convolutional Neural Network (CNN). The generalization property of CNN is poor for satellite imagery because the data can be very diverse in terms of landscape types, image resolutions, and scarcity of labels for different geographies and seasons. Hence, the performance of CNN doesn't translate well to images from unseen regions or seasons. Inspired by Conditional Generative Adversarial Networks (CGAN) based approach of image-to-image translation for high-resolution satellite imagery, we propose a CGAN framework for land cover classification using medium-resolution Sentinel-2 imagery. We find that the CGAN model outperforms the CNN model of similar complexity by a significant margin on an unseen imbalanced test dataset.