Learning Multi-Scale Deep Features for High-Resolution Satellite Image Classification
This work addresses satellite image classification, which is important for remote sensing applications, but it is incremental as it builds on existing deep learning and pooling techniques.
The authors tackled high-resolution satellite image classification by proposing a multi-scale deep feature learning method that uses spatial pyramid pooling networks and multiple kernel learning, achieving favorable performance compared to state-of-the-art methods on two difficult datasets.
In this paper, we propose a multi-scale deep feature learning method for high-resolution satellite image classification. Specifically, we firstly warp the original satellite image into multiple different scales. The images in each scale are employed to train a deep convolutional neural network (DCNN). However, simultaneously training multiple DCNNs is time-consuming. To address this issue, we explore DCNN with spatial pyramid pooling (SPP-net). Since different SPP-nets have the same number of parameters, which share the identical initial values, and only fine-tuning the parameters in fully-connected layers ensures the effectiveness of each network, thereby greatly accelerating the training process. Then, the multi-scale satellite images are fed into their corresponding SPP-nets respectively to extract multi-scale deep features. Finally, a multiple kernel learning method is developed to automatically learn the optimal combination of such features. Experiments on two difficult datasets show that the proposed method achieves favorable performance compared to other state-of-the-art methods.