# ViT-P: Rethinking Data-efficient Vision Transformers from Locality

arXiv: https://arxiv.org/abs/2203.02358 · HTML: https://mlsanity.com/paper/2203.02358/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 28 references that are in the map.
- First posted on arXiv 4 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [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)
- [Revisiting Unreasonable Effectiveness of Data in Deep Learning Era](https://mlsanity.com/paper/1707.02968/) (2017)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [Bottleneck Transformers for Visual Recognition](https://mlsanity.com/paper/2101.11605/) (2021)
- [On the Relationship between Self-Attention and Convolutional Layers](https://mlsanity.com/paper/1911.03584/) (2019)
- [Escaping the Big Data Paradigm with Compact Transformers](https://mlsanity.com/paper/2104.05704/) (2021)
- [LocalViT: Analyzing Locality in Vision Transformers](https://mlsanity.com/paper/2104.05707/) (2021)
- [Scaling Local Self-Attention for Parameter Efficient Visual Backbones](https://mlsanity.com/paper/2103.12731/) (2021)
- [Visformer: The Vision-friendly Transformer](https://mlsanity.com/paper/2104.12533/) (2021)
- [Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding](https://mlsanity.com/paper/2105.12723/) (2021)

## Built on by (most cited first, 4 of 4)

- [Hydra Attention: Efficient Attention with Many Heads](https://mlsanity.com/paper/2209.07484/) (2022)
- [Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?](https://mlsanity.com/paper/2401.12902/) (2024)
- [Inference Time Evidences of Adversarial Attacks for Forensic on Transformers](https://mlsanity.com/paper/2301.13356/) (2023)
- [Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation](https://mlsanity.com/paper/2311.18735/) (2023)

## Abstract (arXiv)

Recent advances of Transformers have brought new trust to computer vision tasks. However, on small dataset, Transformers is hard to train and has lower performance than convolutional neural networks. We make vision transformers as data-efficient as convolutional neural networks by introducing multi-focal attention bias. Inspired by the attention distance in a well-trained ViT, we constrain the self-attention of ViT to have multi-scale localized receptive field. The size of receptive field is adaptable during training so that optimal configuration can be learned. We provide empirical evidence that proper constrain of receptive field can reduce the amount of training data for vision transformers. On Cifar100, our ViT-P Base model achieves the state-of-the-art accuracy (83.16%) trained from scratch. We also perform analysis on ImageNet to show our method does not lose accuracy on large data sets.