Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classification
This work addresses the challenge of efficiently applying ConvNets in remote sensing where labeled data and computational resources are limited, though it is incremental as it compares established strategies.
The paper analyzed three strategies (full training, fine-tuning, and feature extraction) for adapting existing convolutional neural networks to remote sensing scene classification, finding that fine-tuning with a linear SVM achieved state-of-the-art results on three datasets.
We present an analysis of three possible strategies for exploiting the power of existing convolutional neural networks (ConvNets) in different scenarios from the ones they were trained: full training, fine tuning, and using ConvNets as feature extractors. In many applications, especially including remote sensing, it is not feasible to fully design and train a new ConvNet, as this usually requires a considerable amount of labeled data and demands high computational costs. Therefore, it is important to understand how to obtain the best profit from existing ConvNets. We perform experiments with six popular ConvNets using three remote sensing datasets. We also compare ConvNets in each strategy with existing descriptors and with state-of-the-art baselines. Results point that fine tuning tends to be the best performing strategy. In fact, using the features from the fine-tuned ConvNet with linear SVM obtains the best results. We also achieved state-of-the-art results for the three datasets used.