TreeFormers -- An Exploration of Vision Transformers for Deforestation Driver Classification

TL;DR

This paper explores the use of vision transformers to classify deforestation drivers from satellite images, achieving a 72.9% accuracy and offering insights into model performance and limitations.

Contribution

It introduces a ViT-based approach with data augmentation and longitudinal embedding for deforestation driver classification from satellite imagery.

Findings

Achieved 72.9% test accuracy

Enhanced classification with data augmentation techniques

Identified strengths and limitations of ViT in this context

Abstract

This paper addresses the critical issue of deforestation by exploring the application of vision transformers (ViTs) for classifying the drivers of deforestation using satellite imagery from Indonesian forests. Motivated by the urgency of this problem, I propose an approach that leverages ViTs and machine learning techniques. The input to my algorithm is a 332x332-pixel satellite image, and I employ a ViT architecture to predict the deforestation driver class; grassland shrubland, other, plantation, or smallholder agriculture. My methodology involves fine-tuning a pre-trained ViT on a dataset from the Stanford ML Group, and I experiment with rotational data augmentation techniques (among others) and embedding of longitudinal data to improve classification accuracy. I also tried training a ViT from scratch. Results indicate a significant improvement over baseline models, achieving a test accuracy of 72.9%. I conduct a comprehensive analysis, including error patterns and metrics, to highlight the strengths and limitations of my approach. This research contributes to the ongoing efforts to address deforestation challenges through advanced computer vision techniques.