COFGA: Classification Of Fine-Grained Features In Aerial Images

TL;DR

This paper introduces COFGA, a dataset for fine-grained multi-class classification of objects in aerial images, evaluates existing models on this dataset, and discusses the first competition addressing this challenging task.

Contribution

It presents a new dataset COFGA for fine-grained aerial image classification and analyzes model performance, including a novel competition for this problem.

Findings

Existing models show limited accuracy on COFGA

Modified neural networks improve classification performance

The competition fosters progress in fine-grained aerial image analysis

Abstract

Classification between thousands of classes in high-resolution images is one of the heavily studied problems in deep learning over the last decade. However, the challenge of fine-grained multi-class classification of objects in aerial images, especially in low resource cases, is still challenging and an active area of research in the literature. Solving this problem can give rise to various applications in the field of scene understanding and classification and re-identification of specific objects from aerial images. In this paper, we provide a description of our dataset - COFGA of multi-class annotated objects in aerial images. We examine the results of existing state-of-the-art models and modified deep neural networks. Finally, we explain in detail the first published competition for solving this task.