Cross Pseudo Supervision Framework for Sparsely Labelled Geospatial Images

TL;DR

This paper presents a semi-supervised segmentation model using a modified Cross Pseudo Supervision framework to improve land cover mapping accuracy on sparsely labeled high-resolution satellite images across diverse Indian regions.

Contribution

It introduces a novel adaptation of the Cross Pseudo Supervision framework tailored for noisy, sparsely labeled satellite data, enhancing LULC prediction accuracy.

Findings

Improved segmentation accuracy on sparse labels

Robust generalization across diverse geographic areas

Enhanced utility for urban planning applications

Abstract

Land Use Land Cover (LULC) mapping is a vital tool for urban and resource planning, playing a key role in the development of innovative and sustainable cities. This study introduces a semi-supervised segmentation model for LULC prediction using high-resolution satellite images with a vast diversity of data distributions in different areas of India. Our approach ensures a robust generalization across different types of buildings, roads, trees, and water bodies within these distinct areas. We propose a modified Cross Pseudo Supervision framework to train image segmentation models on sparsely labelled data. The proposed framework addresses the limitations of the famous 'Cross Pseudo Supervision' technique for semi-supervised learning, specifically tackling the challenges of training segmentation models on noisy satellite image data with sparse and inaccurate labels. This comprehensive approach significantly enhances the accuracy and utility of LULC mapping, providing valuable insights for urban and resource planning applications.