Preprint · 2026 · Open access
Scale-invariant Gaussian derivative residual networks
arXiv (Cornell University) · Published 3 March 2026 · DOI 10.48550/arxiv.2603.02843
In brief
“Scale-invariant Gaussian derivative residual networks” is a 2026 preprint by Andrzej Perzanowski and Tony Lindeberg, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 1
- Most cited in
- 2026 (1)
- References
- 81
- Authors
- 2
Abstract
Generalisation across image scales remains a fundamental challenge for deep networks, which often fail to handle images at scales not seen during training (the out-of-distribution problem). In this paper, we present provably scale-invariant Gaussian derivative residual networks (GaussDerResNets), constructed out of scale-covariant Gaussian derivative residual blocks coupled in cascade, aimed at addressing this problem. By adding residual skip connections to the previous notion of Gaussian derivative layers, deeper networks with substantially increased accuracy can be constructed, while preserving very good scale generalisation properties. Explicit proofs are provided for the underlying scale-covariant and scale-invariant properties in arbitrary dimensions. To analyse the ability of GaussDerResNets to generalise to new scales, we apply them on a new rescaled version of the STL-10 dataset, where training is done at a single fixed scale and evaluation is performed on copies of the test set, each rescaled to a distinct spatial scale, with scale factors extending over a range of 4. We also conduct similar systematic experiments on the rescaled versions of Fashion-MNIST and CIFAR-10 datasets, and the existing STIR datasets. Experimentally, we demonstrate that the GaussDerResNets have strong scale generalisation and scale selection properties on all the four considered datasets with scaling variations. In our ablation studies, we investigate different architectural variants of GaussDerResNets, demonstrating that basing the architecture on depthwise-separable convolutions reduces the number of parameters and computations, with reasonably maintained accuracy and scale generalisation. We conclude by outlining how the proposed GaussDerResNets can be extended to joint local spatial and scale selection, to address the topic of multi-object detection in a provably scale-invariant manner.
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. (2026). Scale-invariant Gaussian derivative residual networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.02843
MLA 9
Perzanowski, Andrzej, and Tony Lindeberg. “Scale-invariant Gaussian derivative residual networks.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2603.02843.
Chicago
Perzanowski, Andrzej and Tony Lindeberg. 2026. “Scale-invariant Gaussian derivative residual networks.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.02843.
Harvard
Perzanowski, A. and Lindeberg, T. (2026) ‘Scale-invariant Gaussian derivative residual networks’, arXiv (Cornell University). doi:10.48550/arxiv.2603.02843.
IEEE
A. Perzanowski and T. Lindeberg, “Scale-invariant Gaussian derivative residual networks,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2603.02843.
BibTeX
@misc{perzanowski2026scale,
title = {{Scale-invariant Gaussian derivative residual networks}},
author = {Perzanowski, Andrzej and Lindeberg, Tony},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2603.02843},
url = {https://doi.org/10.48550/arxiv.2603.02843}
}
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
- ResNet
- out-of-distribution generalization
- skip connections
- depthwise separable convolution
- scale selection
- multi-target detection
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. (2026). Scale-invariant Gaussian derivative residual networks. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2603.02843
How many times has this paper been cited?
1 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 arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Andrzej Perzanowski, Tony Lindeberg.
What is the DOI of this paper?
10.48550/arxiv.2603.02843, permanently at https://doi.org/10.48550/arxiv.2603.02843. 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.