DropBand: A Simple and Effective Method for Promoting the Scene Classification Accuracy of Convolutional Neural Networks for VHR Remote Sensing Imagery

The dropout and data augmentation techniques are widely used to prevent a convolutional neural network (CNN) from overfitting. However, the dropout technique does not work well when applied to the input channels of neural networks, and data augmentation is usually employed along the image plane. In this letter, we present DropBand, which is a simple and effective method of promoting the classification accuracy of CNNs for very-high-resolution remote sensing image scenes. In DropBand, more training samples are generated by dropping certain spectral bands out of original images. Furthermore, all samples with the same set of spectral bands are collected together to train a base CNN. The final prediction for a test sample is represented by the combination of outputs of all base CNNs. The experimental results for three publicly available data sets, i.e., the SAT-4, SAT-6, and UC-Merced image data sets, show that DropBand can significantly improve the classification accuracy of a CNN.