Data augmentation is a popular technique which helps improve generalization capabilities of deep neural net- works, and can be perceived as implicit regularization. It is widely adopted in scenarios where acquiring high- quality training data is time-consuming and costly, with hyperspectral satellite imaging (HSI) being a real-life example. In this paper, we investigate data augmentation policies (exploiting various techniques, including generative adversarial networks applied to elaborate artificial HSI data) which help improve the generalization of deep neural networks (and other supervised learners) by increasing the representativeness of training sets. Our experimental study performed over HSI benchmarks showed that hyperspectral data augmentation boosts the classification accuracy of the models without sacrificing their real-time inference speed.

© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.

Jakub Nalepa, Michal Myller, Michal Kawulok, and Bogdan Smolka, "On data augmentation for segmenting hyperspectral images," Proc. SPIE 10996, Real-Time Image Processing and Deep Learning 2019, 1099609 (Presented at SPIE Defense + Commercial Sensing: April 15, 2019; Published: 14 May 2019); https://doi.org/10.1117/12.2519517.