RESEARCH ON THE EFFECT OF ACTIVATION FUNCTIONS ON THE ACCURACY OF WATER BODY SEGMENTATION FROM SATELLITE IMAGES
DOI:
https://doi.org/10.34185/1991-7848.itmm.2025.01.102Keywords:
neural network, segmentation, activation function, U-Net, satellite images, Sentinel-2Abstract
A comparative analysis of various activation functions (ReLU, Leaky ReLU, ELU, PReLU, Swish, RReLU) was conducted within a U-Net neural network architecture for the purpose of binary segmentation of water bodies in Sentinel-2 satellite imagery. The experimental design employed a fixed number of training epochs and a consistent set of images, thereby enabling an objective assessment of the results. The findings demonstrate that the selection of the activation function substantially influences the effectiveness of neural network-based segmentation. Among the evaluated functions, Leaky ReLU produced the highest F1 score, as well as superior Precision and IoU values. In contrast, while the ELU function exhibited the highest Recall, its markedly lower Precision indicates a tendency toward over-segmentation. Based on these observations, Leaky ReLU is recommended as the optimal choice for water-body segmentation in satellite images.
References
Viktoriia Hnatushenko, Oleksandr Honcharov. Land cover mapping with Sentinel-2 imagery using deep learning semantic segmentation models.// Proceedings of the X International Scientific Conference "Information Technology and Implementation" (IT&I 2024). - Kyiv, Ukraine, - November 20-21, 2024. – p.1-18 CEUR-WS.org/Vol-3909 - Information Technology and Implementation (IT&I 2024)
Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention. 2015. Vol. 9351. P. 234–241.
Zhou Z., Siddiquee M.M.R., Tajbakhsh N., Liang J. UNet++: A Nested U-Net Architecture for Medical Image Segmentation. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support. 2018. P. 3–11.
Zhang Z., Liu Q., Wang Y. Road Extraction by Deep Residual U-Net. IEEE Geoscience and Remote Sensing Letters. 2018. Vol. 15, Issue 5. P. 749–753.
Shanmugamani R. Deep Learning for Computer Vision: Expert techniques to train advanced neural networks using TensorFlow and Keras. Packt Publishing, 2018. 472 p.
Chollet F. Deep Learning with Python. Manning Publications Co., 2018. 384 p.
