Hydra: an Ensemble of Convolutional Neural Networks for Geospatial Land Classification

TL;DR

Hydra is an ensemble framework of CNNs that enhances geospatial land classification by combining coarse initial training with multiple fine-tuned models, reducing training time while maintaining high accuracy.

Contribution

This paper introduces Hydra, a novel ensemble method that leverages fine-tuning of CNNs with diverse augmentations to improve land classification efficiency and performance.

Findings

Achieved state-of-the-art results on NWPU-RESISC45 dataset.

Maintained high classification accuracy with reduced training time.

Demonstrated effectiveness using ResNet and DenseNet architectures.

Abstract

We describe in this paper Hydra, an ensemble of convolutional neural networks (CNN) for geospatial land classification. The idea behind Hydra is to create an initial CNN that is coarsely optimized but provides a good starting pointing for further optimization, which will serve as the Hydra's body. Then, the obtained weights are fine-tuned multiple times with different augmentation techniques, crop styles, and classes weights to form an ensemble of CNNs that represent the Hydra's heads. By doing so, we prompt convergence to different endpoints, which is a desirable aspect for ensembles. With this framework, we were able to reduce the training time while maintaining the classification performance of the ensemble. We created ensembles for our experiments using two state-of-the-art CNN architectures, ResNet and DenseNet. We have demonstrated the application of our Hydra framework in two datasets, FMOW and NWPU-RESISC45, achieving results comparable to the state-of-the-art for the former and the best reported performance so far for the latter. Code and CNN models are available at https://github.com/maups/hydra-fmow