# Fully trainable Gaussian derivative convolutional layer

Source: [Fully trainable Gaussian derivative convolutional layer](<https://www.sota2.com/research/paper/68fa6d1a1e209131cea37c27>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:25:36.384Z

Authors: Valentin Penaud--Polge, Santiago Velasco-Forero, Jesus Angulo

Published: 2022-07-18T08:16:04.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2207.08424>)

[PDF](<https://arxiv.org/pdf/2207.08424.pdf>)