Translation-Equivariance of Normalization Layers and Aliasing in Convolutional Neural Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916798648025088 |
|---|---|
| author | Scanvic, Jérémy Barthélemy, Quentin Tachella, Julián |
| author_facet | Scanvic, Jérémy Barthélemy, Quentin Tachella, Julián |
| contents | The design of convolutional neural architectures that are exactly equivariant to continuous translations is an active field of research. It promises to benefit scientific computing, notably by making existing imaging systems more physically accurate. Most efforts focus on the design of downsampling/pooling layers, upsampling layers and activation functions, but little attention is dedicated to normalization layers. In this work, we present a novel theoretical framework for understanding the equivariance of normalization layers to discrete shifts and continuous translations. We also determine necessary and sufficient conditions for normalization layers to be equivariant in terms of the dimensions they operate on. Using real feature maps from ResNet-18 and ImageNet, we test those theoretical results empirically and find that they are consistent with our predictions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19805 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Translation-Equivariance of Normalization Layers and Aliasing in Convolutional Neural Networks Scanvic, Jérémy Barthélemy, Quentin Tachella, Julián Computer Vision and Pattern Recognition The design of convolutional neural architectures that are exactly equivariant to continuous translations is an active field of research. It promises to benefit scientific computing, notably by making existing imaging systems more physically accurate. Most efforts focus on the design of downsampling/pooling layers, upsampling layers and activation functions, but little attention is dedicated to normalization layers. In this work, we present a novel theoretical framework for understanding the equivariance of normalization layers to discrete shifts and continuous translations. We also determine necessary and sufficient conditions for normalization layers to be equivariant in terms of the dimensions they operate on. Using real feature maps from ResNet-18 and ImageNet, we test those theoretical results empirically and find that they are consistent with our predictions. |
| title | Translation-Equivariance of Normalization Layers and Aliasing in Convolutional Neural Networks |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.19805 |