2018/10/19 by Philipp Sadler, Sadler, Philipp
Earth and Planetary Sciences · Engineering · Environmental Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Remote Sensing and Land Use #Remote Sensing and LiDAR Applications #Remote Sensing in Agriculture #Remote-Sensing Image Classification
paper · pdf · doi:10.48550/arxiv.1810.08597
openalex publication_date 2018/10/19 · openalex created_date 2022/08/02 · openalex updated_date 2026/07/28
This paper examines, if it is possible to learn structural invariants of city\nimages by using only a single reference picture when producing transformations\nalong the variants in the dataset. Previous work explored the problem of\nlearning from only a few examples and showed that data augmentation techniques\nbenefit performance and generalization for machine learning approaches. First a\nprincipal component analysis in conjunction with a Fourier transform is trained\non a single reference augmentation training dataset using the city images.\nSecondly a convolutional neural network is trained on a similar dataset with\nmore samples. The findings are that the convolutional neural network is capable\nof finding images of the same category whereas the applied principal component\nanalysis in conjunction with a Fourier transform failed to solve this task.\n