Evolutionary Optimization of Neural Architectures in Remote Sensing Classification Problems

Coquelin, Daniel; Götz, Markus; Riedel, Morris; Sedona, Rocco

doi:10.1109/IGARSS47720.2021.9554309

Contribution to a conference proceedings/Contribution to a book

FZJ-2021-02868

Evolutionary Optimization of Neural Architectures in Remote Sensing Classification Problems

Coquelin, D. ; Sedona, R.FZJ* ; Riedel, M. (Corresponding author)FZJ* ; Götz, M.

2021
IEEE

2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS : [Proceedings] - IEEE, 2021. - ISBN 978-1-6654-0369-6 - doi:10.1109/IGARSS47720.2021.9554309
IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2021, Brussels, Belgium, 12 Jul 2021 - 16 Jul 2021 IEEE 1587 - 1590 (2021) [10.1109/IGARSS47720.2021.9554309]

This record in other databases:

Please use a persistent id in citations: http://hdl.handle.net/2128/28856 doi:10.1109/IGARSS47720.2021.9554309

Abstract: BigEarthNet is one of the standard large remote sensing datasets. It has been shown previously that neural networks are effective tools to classify the image patches in this data. However, finding the optimum network hyperparameters and architecture to accurately classify the image patches in BigEarthNet remains a challenge. Searching for more accurate models manually is extremely time consuming and labour intensive. Hence, a systematic approach is advisable. One possibility is automated evolutionary Neural Architecture Search (NAS). With this NAS many of the commonly used network hyperparameters, such as loss functions, are eliminated and a more accurate network is determined.

Contributing Institute(s):