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

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 to form an ensemble of CNNs that represent the Hydra's heads. By doing so, we were able to reduce the training time while maintaining the classification performance of the ensemble. We created ensembles using two state-of-the-art CNN architectures, ResNet and DenseNet, to participate in the Functional Map of the World challenge. With this approach, we finished the competition in third place. We also applied the proposed framework to the NWPU-RESISC45 database and achieved the best reported performance so far. Code and CNN models are available at https://github.com/maups/hydra-fmow