mlsanityData to 14 Oct 2026

Spectral Vision Transformer for Efficient Tokenization with Limited Data

arXiv 2605.12026 ↗First posted 12 May 2026cs.CV cs.AI eess.SPcited by 0

Not on the map. Why?

Abstract (arXiv)

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+.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 61 references that are in the map. First posted on arXiv 12 May 2026.

Builds on

24 of 61 references.

References · 24

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  4. 2018Attention U-Net: Learning Where to Look for the Pancreascited by 1,435
  5. 2021Transformers in Vision: A Surveycited by 1,013
  6. 2016Revisiting Batch Normalization For Practical Domain Adaptationcited by 288
  7. 2021Global Filter Networks for Image Classificationcited by 260
  8. 2020A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promisescited by 231
  9. 2023Frequency-domain MLPs are More Effective Learners in Time Series Forecastingcited by 172
  10. 2020Surgical Data Science -- from Concepts toward Clinical Translationcited by 105
  11. 2022Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learningcited by 78
  12. 2022Locality Guidance for Improving Vision Transformers on Tiny Datasetscited by 33
12 more
  1. 2024Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenizationcited by 27
  2. 2024Spectral Image Tokenizercited by 15
  3. 2023A Review of Predictive and Contrastive Self-supervised Learning for Medical Imagescited by 10
  4. 2022Prior Knowledge-Guided Attention in Self-Supervised Vision Transformerscited by 7
  5. 2025Denoising Vision Transformer Autoencoder with Spectral Self-Regularizationcited by 7
  6. 2022A Comparative Study of Graph Neural Networks for Shape Classification in Neuroimagingcited by 3
  7. 2025FreDFT: Frequency Domain Fusion Transformer for Visible-Infrared Object Detectioncited by 3
  8. 2023Maximum Spherical Mean Value (mSMV) Filtering for Whole Brain Quantitative Susceptibility Mappingcited by 2
  9. 2025Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learningcited by 2
  10. 2022Explicitly Increasing Input Information Density for Vision Transformers on Small Datasetscited by 1
  11. 2025Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosiscited by 1
  12. 2025Three-dimensional end-to-end deep learning for brain MRI analysiscited by 1

Built on by

Not cited yet.