Conference paper · 2022 · Open access
Fully Trainable Gaussian Derivative Convolutional Layer
Proceedings - International Conference on Image Processing, 2421–2425 · Published 16 October 2022 · DOI 10.1109/icip46576.2022.9897734
In brief
“Fully Trainable Gaussian Derivative Convolutional Layer” is a 2022 conference paper by Valentin Penaud--Polge and 2 co-authors, published in Proceedings - International Conference on Image Processing. OpenAlex counts 16 citations as of 16 November 2026, which puts it in the top 7% of works published in 2022 by citations. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 16
- Most cited in
- 2023 (5)
- Field-weighted impact
- 1.13
- References
- 27
- Authors
- 3
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.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Penaud--Polge, V., Velasco-Forero, S., & Angulo, J. (2022). Fully Trainable Gaussian Derivative Convolutional Layer. Proceedings - International Conference on Image Processing, 2421–2425. https://doi.org/10.1109/icip46576.2022.9897734
MLA 9
Penaud--Polge, Valentin, et al. “Fully Trainable Gaussian Derivative Convolutional Layer.” Proceedings - International Conference on Image Processing, 2022, pp. 2421–2425. https://doi.org/10.1109/icip46576.2022.9897734.
Chicago
Penaud--Polge, Valentin, Santiago Velasco-Forero, and Jesús Angulo. 2022. “Fully Trainable Gaussian Derivative Convolutional Layer.” Proceedings - International Conference on Image Processing: 2421–2425. https://doi.org/10.1109/icip46576.2022.9897734.
Harvard
Penaud--Polge, V., Velasco-Forero, S. and Angulo, J. (2022) ‘Fully Trainable Gaussian Derivative Convolutional Layer’, Proceedings - International Conference on Image Processing, pp. 2421–2425. doi:10.1109/icip46576.2022.9897734.
IEEE
V. Penaud--Polge, S. Velasco-Forero, and J. Angulo, “Fully Trainable Gaussian Derivative Convolutional Layer,” Proceedings - International Conference on Image Processing, pp. 2421–2425, 2022, doi: 10.1109/icip46576.2022.9897734.
BibTeX
@inproceedings{penaudpolge2022fully,
title = {{Fully Trainable Gaussian Derivative Convolutional Layer}},
author = {Penaud--Polge, Valentin and Velasco-Forero, Santiago and Angulo, Jesús},
booktitle = {Proceedings - International Conference on Image Processing},
year = {2022},
pages = {2421--2425},
doi = {10.1109/icip46576.2022.9897734},
url = {https://doi.org/10.1109/icip46576.2022.9897734}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2022 | 2 | |
| 2023 | 5 | |
| 2024 | 3 | |
| 2025 | 4 | |
| 2026 | 2 |
Its field-weighted citation impact is 1.13: it has been cited 1.13 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- anisotropic kernels
- image classification
- image segmentation
- VGG16
- U-Net
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Penaud--Polge, V., Velasco-Forero, S., & Angulo, J. (2022). Fully Trainable Gaussian Derivative Convolutional Layer. Proceedings - International Conference on Image Processing, 2421–2425. https://doi.org/10.1109/icip46576.2022.9897734
How many times has this paper been cited?
16 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access: read the free full text at arXiv (Cornell University).
Who wrote this paper?
Valentin Penaud--Polge, Santiago Velasco-Forero, Jesús Angulo.
What is the DOI of this paper?
10.1109/icip46576.2022.9897734. The permanent link is https://doi.org/10.1109/icip46576.2022.9897734.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.