The Gaussian kernel and its derivatives have already been employed for Convolutional Neural Networks in several previous works. Most of these papers proposed to compute filters by linearly combining one or several bases of fixed or slightly trainable Gaussian kernels with or without their derivatives. In this article, we propose a high-level configurable layer based on anisotropic, oriented and shifted Gaussian derivative kernels which generalize notions encountered in previous related works while keeping their main advantage. The results show that the proposed layer has competitive performance compared to previous works and that it can be successfully included in common deep architectures such as VGG16 for image classification and U-net for image segmentation.
@article{arxiv.2207.08424,
title = {Fully trainable Gaussian derivative convolutional layer},
author = {Valentin Penaud--Polge and Santiago Velasco-Forero and Jesus Angulo},
journal= {arXiv preprint arXiv:2207.08424},
year = {2022}
}