Papers › An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures

An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures

14 Jan 2025arXiv:2501.07930archive 2025-07-28

Thibaut Boissin, Franck Mamalet, Thomas Fel, Agustin Martin Picard, Thomas Massena, Mathieu Serrurier

Orthogonal convolutional layers are the workhorse of multiple areas in machine learning, such as adversarial robustness, normalizing flows, GANs, and Lipschitzconstrained models. Their ability to preserve norms and ensure stable gradient propagation makes them valuable for a large range of problems. Despite their promise, the deployment of orthogonal convolution in large-scale applications is a significant challenge due to computational overhead and limited support for modern features like strides, dilations, group convolutions, and transposed convolutions.In this paper, we introduce AOC (Adaptative Orthogonal Convolution), a scalable method for constructing orthogonal convolutions, effectively overcoming these limitations. This advancement unlocks the construction of architectures that were previously considered impractical. We demonstrate through our experiments that our method produces expressive models that become increasingly efficient as they scale. To foster further advancement, we provide an open-source library implementing this method, available at https://github.com/thib-s/orthogonium.

PaperPDFCode

Code

thib-s/orthogonium officialmentioned in papermentioned on GitHubpytorch report
deel-ai/orthogonium mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Adversarial Robustness

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Convolution

1 archive method tag without a method page not shown.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections