Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.09667 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913109623439360 |
|---|---|
| author | Heruth, Albert |
| author_facet | Heruth, Albert |
| contents | We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathematically guaranteed rotation invariance without data augmentation. In this Paper, we also made a comparison to other neural network architectures (CNN`s). Have a look at the results and feel free to contact me for any questions. This is my first paper:) Made by Hackbert |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_09667 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | S2P-Net: A Spectral-Spatial Polar Network for Rotation-Invariant Object Recognition in Low-Data Regimes Heruth, Albert Computer Vision and Pattern Recognition Artificial Intelligence We present S2P-Net (Spectral-Spatial Polar Network), a compact deep learning architecture that achieves mathematically guaranteed rotation invariance without data augmentation. In this Paper, we also made a comparison to other neural network architectures (CNN`s). Have a look at the results and feel free to contact me for any questions. This is my first paper:) Made by Hackbert |
| title | S2P-Net: A Spectral-Spatial Polar Network for Rotation-Invariant Object Recognition in Low-Data Regimes |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.09667 |