Publikation
Deep Neural Networks for Analysis of Microscopy Images—Synthetic Data Generation and Adaptive Sampling
Patrick Trampert; Dmitri Rubinstein; Faysal Boughorbel; Christian Schlinkmann; Maria Luschkova; Philipp Slusallek; Tim Dahmen; Stefan Sandfeld
In: Paolo Olivero (Hrsg.). Crystals, Vol. 11, No. 258, Pages 1-13, MDPI, 3/2021.
Zusammenfassung
The analysis of microscopy images has always been an important yet time consuming process in materials science. Convolutional Neural Networks (CNNs) have been very successfully used for a number of tasks, such as image segmentation. However, training a CNN requires a large amount of hand annotated data, which can be a problem for material science data. We present a procedure to generate synthetic data based on ad hoc parametric data modelling for enhancing generalization of trained neural network models. Especially for situations where it is not possible to gather a lot of data, such an approach is beneficial and may enable to train a neural network reasonably. Furthermore, we show that targeted data generation by adaptively sampling the parameter space of the generative models gives superior results compared to generating random data points.