# Explicitly Increasing Input Information Density for Vision Transformers on Small Datasets

arXiv: https://arxiv.org/abs/2210.14319 · HTML: https://mlsanity.com/paper/2210.14319/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 43 references that are in the map.
- First posted on arXiv 25 Oct 2022.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference](https://mlsanity.com/paper/2104.01136/) (2021)
- [Early Convolutions Help Transformers See Better](https://mlsanity.com/paper/2106.14881/) (2021)
- [CMT: Convolutional Neural Networks Meet Vision Transformers](https://mlsanity.com/paper/2107.06263/) (2021)
- [Focal Self-attention for Local-Global Interactions in Vision Transformers](https://mlsanity.com/paper/2107.00641/) (2021)
- [Incorporating Convolution Designs into Visual Transformers](https://mlsanity.com/paper/2103.11816/) (2021)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [LocalViT: Analyzing Locality in Vision Transformers](https://mlsanity.com/paper/2104.05707/) (2021)
- [Co-Scale Conv-Attentional Image Transformers](https://mlsanity.com/paper/2104.06399/) (2021)
- [Learning in the Frequency Domain](https://mlsanity.com/paper/2002.12416/) (2020)
- [Vision Transformer for Small-Size Datasets](https://mlsanity.com/paper/2112.13492/) (2021)
- [Efficient Training of Visual Transformers with Small Datasets](https://mlsanity.com/paper/2106.03746/) (2021)
- [Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding](https://mlsanity.com/paper/2105.12723/) (2021)
- [Less is More: Pay Less Attention in Vision Transformers](https://mlsanity.com/paper/2105.14217/) (2021)
- [Deep Residual Learning in the JPEG Transform Domain](https://mlsanity.com/paper/1812.11690/) (2018)
- [How to Train Vision Transformer on Small-scale Datasets?](https://mlsanity.com/paper/2210.07240/) (2022)
- [Deep Feature Augmentation for Occluded Image Classification](https://mlsanity.com/paper/2011.00768/) (2020)
- [Audio-Visual Transformer Based Crowd Counting](https://mlsanity.com/paper/2109.01926/) (2021)

## Built on by (most cited first, 1 of 1)

- [Spectral Vision Transformer for Efficient Tokenization with Limited Data](https://mlsanity.com/paper/2605.12026/) (2026)

## Abstract (arXiv)

Vision Transformers have attracted a lot of attention recently since the successful implementation of Vision Transformer (ViT) on vision tasks. With vision Transformers, specifically the multi-head self-attention modules, networks can capture long-term dependencies inherently. However, these attention modules normally need to be trained on large datasets, and vision Transformers show inferior performance on small datasets when training from scratch compared with widely dominant backbones like ResNets. Note that the Transformer model was first proposed for natural language processing, which carries denser information than natural images. To boost the performance of vision Transformers on small datasets, this paper proposes to explicitly increase the input information density in the frequency domain. Specifically, we introduce selecting channels by calculating the channel-wise heatmaps in the frequency domain using Discrete Cosine Transform (DCT), reducing the size of input while keeping most information and hence increasing the information density. As a result, 25% fewer channels are kept while better performance is achieved compared with previous work. Extensive experiments demonstrate the effectiveness of the proposed approach on five small-scale datasets, including CIFAR-10/100, SVHN, Flowers-102, and Tiny ImageNet. The accuracy has been boosted up to 17.05% with Swin and Focal Transformers. Codes are available at https://github.com/xiangyu8/DenseVT.