Generalizing Deep Models for Overhead Image Segmentation Through Getis-Ord Gi* Pooling

TL;DR

This paper introduces a novel pooling method for deep learning models in geospatial image analysis, leveraging geostatistical principles to improve generalization in overhead image segmentation tasks.

Contribution

The paper proposes a new Getis-Ord Gi* pooling technique that incorporates geostatistical rules to enhance deep model generalization across different geographic scenarios.

Findings

Getis-Ord Gi* pooling outperforms standard pooling in generalization.

Improved segmentation accuracy with limited training data.

Enhanced model robustness across diverse geographic locations.

Abstract

That most deep learning models are purely data driven is both a strength and a weakness. Given sufficient training data, the optimal model for a particular problem can be learned. However, this is usually not the case and so instead the model is either learned from scratch from a limited amount of training data or pre-trained on a different problem and then fine-tuned. Both of these situations are potentially suboptimal and limit the generalizability of the model. Inspired by this, we investigate methods to inform or guide deep learning models for geospatial image analysis to increase their performance when a limited amount of training data is available or when they are applied to scenarios other than which they were trained on. In particular, we exploit the fact that there are certain fundamental rules as to how things are distributed on the surface of the Earth and these rules do not vary substantially between locations. Based on this, we develop a novel feature pooling method for convolutional neural networks using Getis-Ord Gi* analysis from geostatistics. Experimental results show our proposed pooling function has significantly better generalization performance compared to a standard data-driven approach when applied to overhead image segmentation.