Abstract:Normalization Equivariance (NE), equivariance to global contrast and brightness transforms, improves robustness to distribution shift in image-to-image prediction. Existing methods enforce this prior by constraining internal layers to NE-compatible families, limiting compatibility with standard components such as attention and LayerNorm, and adding runtime cost. We characterize the full NE function class: a function is NE if and only if it admits a normalize-process-denormalize factorization. This turns exact NE enforcement, for the ideal wrapper, from an internal architectural constraint into an input-output parameterization problem, allowing a parameter-free wrapper (WNE) to enforce NE around any backbone, including transformers. In a single-noise mismatch diagnostic for blind denoising, the wrapper improves CNN and transformer robustness with no measurable GPU overhead; architectural NE baselines incur up to a 1.6x slowdown.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.08193 [cs.CV] |
| (or arXiv:2605.08193v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08193 arXiv-issued DOI via DataCite |
Submission history
From: Youssef Saied [view email]
[v1]
Tue, 5 May 2026 17:40:52 UTC (1,408 KB)