Journal article · 2025 · Open access
Scale Generalisation Properties of Extended Scale-Covariant and Scale-Invariant Gaussian Derivative Networks on Image Datasets with Spatial Scaling Variations
Journal of Mathematical Imaging and Vision, 67(3) · Published 12 May 2025 · DOI 10.1007/s10851-025-01245-x
In brief
“Scale Generalisation Properties of Extended Scale-Covariant and Scale-Invariant Gaussian Derivative Networks on Image Datasets with Spatial Scaling Variations” is a 2025 journal article by Andrzej Perzanowski and Tony Lindeberg, published in Journal of Mathematical Imaging and Vision. OpenAlex counts 7 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at Journal of Mathematical Imaging and Vision.
- Citations
- 7
- Most cited in
- 2026 (5)
- Field-weighted impact
- 1.18
- References
- 88
- Authors
- 2
Abstract
Due to the variabilities in image structures caused by perspective scaling transformations, it is essential for deep networks to have an ability to generalise to scales not seen during training. This paper presents an in-depth analysis of the scale generalisation properties of the scale-covariant and scale-invariant Gaussian derivative networks, complemented with both conceptual and algorithmic extensions. For this purpose, Gaussian derivative networks (GaussDerNets) are evaluated on new rescaled versions of the Fashion-MNIST and the CIFAR-10 datasets, with spatial scaling variations over a factor of 4 in the testing data, that are not present in the training data. Additionally, evaluations on the previously existing STIR datasets show that the GaussDerNets achieve better scale generalisation than previously reported for these datasets for other types of deep networks. We first experimentally demonstrate that the GaussDerNets have quite good scale generalisation properties on the new datasets and that average pooling of feature responses over scales may sometimes also lead to better results than the previously used approach of max pooling over scales. Then, we demonstrate that using a spatial max pooling mechanism after the final layer enables localisation of non-centred objects in the image domain, with maintained scale generalisation properties. We also show that regularisation during training, by applying dropout across the scale channels, referred to as scale-channel dropout, improves both the performance and the scale generalisation. In additional ablation studies, we show that, for the rescaled CIFAR-10 dataset, basing the layers in the GaussDerNets on derivatives up to order three leads to better performance and scale generalisation for coarser scales, whereas networks based on derivatives up to order two achieve better scale generalisation for finer scales. Moreover, we demonstrate that discretisations of GaussDerNets based on the discrete analogue of the Gaussian kernel in combination with central difference operators perform best or among the best, compared to a set of other discrete approximations of the Gaussian derivative kernels. Furthermore, we show that the improvement in performance obtained by learning the scale values of the Gaussian derivatives, as opposed to using the previously proposed choice of a fixed logarithmic distribution of the scale levels, is usually only minor, thus supporting the previously postulated choice of using a logarithmic distribution as a very reasonable prior. Finally, by visualising the activation maps and the learned receptive fields, we demonstrate that the GaussDerNets have very good explainability properties.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Perzanowski, A., & Lindeberg, T. (2025). Scale Generalisation Properties of Extended Scale-Covariant and Scale-Invariant Gaussian Derivative Networks on Image Datasets with Spatial Scaling Variations. Journal of Mathematical Imaging and Vision, 67(3). https://doi.org/10.1007/s10851-025-01245-x
MLA 9
Perzanowski, Andrzej, and Tony Lindeberg. “Scale Generalisation Properties of Extended Scale-Covariant and Scale-Invariant Gaussian Derivative Networks on Image Datasets with Spatial Scaling Variations.” Journal of Mathematical Imaging and Vision, vol. 67, no. 3, 2025. https://doi.org/10.1007/s10851-025-01245-x.
Chicago
Perzanowski, Andrzej and Tony Lindeberg. 2025. “Scale Generalisation Properties of Extended Scale-Covariant and Scale-Invariant Gaussian Derivative Networks on Image Datasets with Spatial Scaling Variations.” Journal of Mathematical Imaging and Vision 67 (3). https://doi.org/10.1007/s10851-025-01245-x.
Harvard
Perzanowski, A. and Lindeberg, T. (2025) ‘Scale Generalisation Properties of Extended Scale-Covariant and Scale-Invariant Gaussian Derivative Networks on Image Datasets with Spatial Scaling Variations’, Journal of Mathematical Imaging and Vision, 67(3). doi:10.1007/s10851-025-01245-x.
IEEE
A. Perzanowski and T. Lindeberg, “Scale Generalisation Properties of Extended Scale-Covariant and Scale-Invariant Gaussian Derivative Networks on Image Datasets with Spatial Scaling Variations,” Journal of Mathematical Imaging and Vision, vol. 67, no. 3, 2025, doi: 10.1007/s10851-025-01245-x.
BibTeX
@article{perzanowski2025scale,
title = {{Scale Generalisation Properties of Extended Scale-Covariant and Scale-Invariant Gaussian Derivative Networks on Image Datasets with Spatial Scaling Variations}},
author = {Perzanowski, Andrzej and Lindeberg, Tony},
journal = {Journal of Mathematical Imaging and Vision},
year = {2025},
volume = {67},
number = {3},
doi = {10.1007/s10851-025-01245-x},
url = {https://doi.org/10.1007/s10851-025-01245-x}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- scale invariance
- scale covariance
- spatial scaling
- higher-order derivatives
- receptive fields
- explainability
- Fashion-MNIST
- CIFAR-10
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?
Perzanowski, A., & Lindeberg, T. (2025). Scale Generalisation Properties of Extended Scale-Covariant and Scale-Invariant Gaussian Derivative Networks on Image Datasets with Spatial Scaling Variations. Journal of Mathematical Imaging and Vision, 67(3). https://doi.org/10.1007/s10851-025-01245-x
How many times has this paper been cited?
7 times, according to OpenAlex on 18 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 at Journal of Mathematical Imaging and Vision: sign in and open the PDF from this page.
Who wrote this paper?
Andrzej Perzanowski, Tony Lindeberg.
What is the DOI of this paper?
10.1007/s10851-025-01245-x, permanently at https://doi.org/10.1007/s10851-025-01245-x. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.