Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.12026 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916004860264448 |
|---|---|
| author | Roberts, Alexandra G. John, Maneesh Zhang, Jinwei Romano, Dominick Sisman, Mert Choi, Ki Sueng Kim, Heejong Sabuncu, Mert R. Nguyen, Thanh D. Dimov, Alexey V. Spincemaille, Pascal Kopell, Brian H. Wang, Yi |
| author_facet | Roberts, Alexandra G. John, Maneesh Zhang, Jinwei Romano, Dominick Sisman, Mert Choi, Ki Sueng Kim, Heejong Sabuncu, Mert R. Nguyen, Thanh D. Dimov, Alexey V. Spincemaille, Pascal Kopell, Brian H. Wang, Yi |
| contents | We propose a novel spectral vision transformer architecture for efficient tokenization in limited data, with an emphasis on medical imaging. We outline convenient theoretical properties arising from the choice of basis including spatial invariance and optimal signal-to-noise ratio. We show reduced complexity arising from the spectral projection compared to spatial vision transformers. We show equitable or superior performance with a reduced number of parameters as compared to a variety of models including compact and standard vision transformers, convolutional neural networks with attention, shifted window transformers, multi-layer perceptrons, and logistic regression. We include simulated, public, and clinical data in our analysis and release our code at: \verb+github.com/agr78/spectralViT+. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_12026 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Spectral Vision Transformer for Efficient Tokenization with Limited Data Roberts, Alexandra G. John, Maneesh Zhang, Jinwei Romano, Dominick Sisman, Mert Choi, Ki Sueng Kim, Heejong Sabuncu, Mert R. Nguyen, Thanh D. Dimov, Alexey V. Spincemaille, Pascal Kopell, Brian H. Wang, Yi Computer Vision and Pattern Recognition Artificial Intelligence Signal Processing We propose a novel spectral vision transformer architecture for efficient tokenization in limited data, with an emphasis on medical imaging. We outline convenient theoretical properties arising from the choice of basis including spatial invariance and optimal signal-to-noise ratio. We show reduced complexity arising from the spectral projection compared to spatial vision transformers. We show equitable or superior performance with a reduced number of parameters as compared to a variety of models including compact and standard vision transformers, convolutional neural networks with attention, shifted window transformers, multi-layer perceptrons, and logistic regression. We include simulated, public, and clinical data in our analysis and release our code at: \verb+github.com/agr78/spectralViT+. |
| title | Spectral Vision Transformer for Efficient Tokenization with Limited Data |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Signal Processing |
| url | https://arxiv.org/abs/2605.12026 |