Abstract
The deep convolutional neural network (DeCNN) is considered one of promising techniques for classifying the high-spatial-resolution remote sensing (HSRRS) scenes, due to its powerful feature extraction capabilities. It is well-known that huge high-quality labeled datasets are required for achieving the better classification performances and preventing overfitting, during the training DeCNN model process. However, the lack of high-quality datasets limits the applications of DeCNN. In order to solve this problem, in this article, we propose a HSRRS image scene classification method using transfer learning and the DeCNN (TL-DeCNN) model in a few shot HSRRS scene samples. Specifically, three typical DeCNNs of VGG19, ResNet50, and InceptionV3, trained on the ImageNet2015, the weights of their convolutional layer for that of the TL-DeCNN are transferred, respectively. Then, TL-DeCNN just needs to fine-tune its classification module on the few shot HSRRS scene samples in a few epochs. Experimental results indicate that our proposed TL-DeCNN method provides absolute dominance results without overfitting, when compared with the VGG19, ResNet50, and InceptionV3, directly trained on the few shot samples.
Highlights
W ITH the development of satellite remote sensing and computer technology, the spatial resolution and texture information of remote sensing image have been improved and corresponding processing approaches have been updated
The second one is limited labeled High-spatial-resolution remote sensing (HSRRS) image scene classification based on TL-deep convolutional neural network (CNN) (DeCNN), which means transferring the knowledge trained by VGG19, ResNet50, and InceptionV3 based on ImageNet2015, to the target limited labeled HSRRS image dataset to make classification, respectively
For few shot learning, InceptionV3 obtains the best overall accuracy (OA) and kappa coefficient (KC), and after adding the transferred knowledge the TLResNet50 gets the best performance in OA and KC
Summary
W ITH the development of satellite remote sensing and computer technology, the spatial resolution and texture information of remote sensing image have been improved and corresponding processing approaches have been updated. A lot of HSRRS images have been acquired and significant efforts have been made for land use land cover (LULC) scene classification in the field of pattern recognition [4], [5] These approaches extract features first from training data and build a classification model for testing other data. The convolutional neural network (CNN) is one of typical deep learning algorithms, and many types of algorithms based on CNN (e.g., ResNet, VGG, Inception) have been developed in computer vision, natural language processing, medical, and remote sensing image processing [13] These practical applications indicated that the depth of a network is vital for the model, when adding layers to the network, it can extract more complex features. Several studies have shown that transfer learning get a good performance in classification and recognition for small scale training data [14]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
