Detecting cities in aerial night-time images by learning structural invariants using single reference augmentation
This addresses the challenge of data-efficient learning for aerial image analysis, but it is incremental as it builds on prior work on few-shot learning and augmentation.
The paper tackled the problem of learning structural invariants for city detection in aerial night-time images using only a single reference picture for augmentation, finding that a convolutional neural network succeeded in identifying city images while a PCA-Fourier transform method failed.
This paper examines, if it is possible to learn structural invariants of city images by using only a single reference picture when producing transformations along the variants in the dataset. Previous work explored the problem of learning from only a few examples and showed that data augmentation techniques benefit performance and generalization for machine learning approaches. First a principal component analysis in conjunction with a Fourier transform is trained on a single reference augmentation training dataset using the city images. Secondly a convolutional neural network is trained on a similar dataset with more samples. The findings are that the convolutional neural network is capable of finding images of the same category whereas the applied principal component analysis in conjunction with a Fourier transform failed to solve this task.