# LocalViT: Analyzing Locality in Vision Transformers

arXiv: https://arxiv.org/abs/2104.05707 · HTML: https://mlsanity.com/paper/2104.05707/

## Key facts

- Cited by 228 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 12 Apr 2021.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [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)
- [Incorporating Convolution Designs into Visual Transformers](https://mlsanity.com/paper/2103.11816/) (2021)
- [Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding](https://mlsanity.com/paper/2103.15358/) (2021)
- [Non-Local Recurrent Network for Image Restoration](https://mlsanity.com/paper/1806.02919/) (2018)
- [HAT: Hardware-Aware Transformers for Efficient Natural Language Processing](https://mlsanity.com/paper/2005.14187/) (2020)
- [Lite Transformer with Long-Short Range Attention](https://mlsanity.com/paper/2004.11886/) (2020)
- [BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search](https://mlsanity.com/paper/2103.12424/) (2021)
- [DeLighT: Deep and Light-weight Transformer](https://mlsanity.com/paper/2008.00623/) (2020)

## Built on by (most cited first, 30 of 228)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Uformer: A General U-Shaped Transformer for Image Restoration](https://mlsanity.com/paper/2106.03106/) (2021)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [MixFormer: End-to-End Tracking with Iterative Mixed Attention](https://mlsanity.com/paper/2203.11082/) (2022)
- [Vision Transformers for Single Image Dehazing](https://mlsanity.com/paper/2204.03883/) (2022)
- [TransWeather: Transformer-based Restoration of Images Degraded by Adverse Weather Conditions](https://mlsanity.com/paper/2111.14813/) (2021)
- [EfficientFormer: Vision Transformers at MobileNet Speed](https://mlsanity.com/paper/2206.01191/) (2022)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias](https://mlsanity.com/paper/2106.03348/) (2021)
- [Learning A Sparse Transformer Network for Effective Image Deraining](https://mlsanity.com/paper/2303.11950/) (2023)
- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [Focal Modulation Networks](https://mlsanity.com/paper/2203.11926/) (2022)
- [DaViT: Dual Attention Vision Transformers](https://mlsanity.com/paper/2204.03645/) (2022)
- [Recurrent Video Restoration Transformer with Guided Deformable Attention](https://mlsanity.com/paper/2206.02146/) (2022)
- [Separable Self-attention for Mobile Vision Transformers](https://mlsanity.com/paper/2206.02680/) (2022)
- [Efficient Long-Range Attention Network for Image Super-resolution](https://mlsanity.com/paper/2203.06697/) (2022)
- [Transformer for Single Image Super-Resolution](https://mlsanity.com/paper/2108.11084/) (2021)
- [HRFormer: High-Resolution Transformer for Dense Prediction](https://mlsanity.com/paper/2110.09408/) (2021)
- [Efficient and Explicit Modelling of Image Hierarchies for Image Restoration](https://mlsanity.com/paper/2303.00748/) (2023)
- [Not All Images are Worth 16x16 Words: Dynamic Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2105.15075/) (2021)
- [Towards Robust Vision Transformer](https://mlsanity.com/paper/2105.07926/) (2021)
- [RegionViT: Regional-to-Local Attention for Vision Transformers](https://mlsanity.com/paper/2106.02689/) (2021)
- [Vision Transformer for Small-Size Datasets](https://mlsanity.com/paper/2112.13492/) (2021)

## Abstract (arXiv)

The aim of this paper is to study the influence of locality mechanisms in vision transformers. Transformers originated from machine translation and are particularly good at modelling long-range dependencies within a long sequence. Although the global interaction between the token embeddings could be well modelled by the self-attention mechanism of transformers, what is lacking is a locality mechanism for information exchange within a local region. In this paper, locality mechanism is systematically investigated by carefully designed controlled experiments. We add locality to vision transformers into the feed-forward network. This seemingly simple solution is inspired by the comparison between feed-forward networks and inverted residual blocks. The importance of locality mechanisms is validated in two ways: 1) A wide range of design choices (activation function, layer placement, expansion ratio) are available for incorporating locality mechanisms and proper choices can lead to a performance gain over the baseline, and 2) The same locality mechanism is successfully applied to vision transformers with different architecture designs, which shows the generalization of the locality concept. For ImageNet2012 classification, the locality-enhanced transformers outperform the baselines Swin-T, DeiT-T, and PVT-T by 1.0%, 2.6% and 3.1% with a negligible increase in the number of parameters and computational effort. Code is available at https://github.com/ofsoundof/LocalViT.