Five-fold training dataset of fossil pollen images from Burgäschisee used for automated fossil pollen identification (von Allmen et al. study)

This dataset consists of a training dataset for the CNN model containing pollen grain images of nine common pollen taxa, one marker class (Lycopodium clavatum) and four abundant non-pollen debris classes. The dataset was split five-times so that each image is part of the validation dataset in just one of these splits. Additionally, the dataset contains annotated images used to train the object detection model and a dataset of images that were used to evaluate the performance of the CNN model. For further information on the datsets themselves and how they were used the reader may refer to the github repository here attached (https://github.com/RobinVonAllmen/FOSSILPOLLEN)