# MicroViT: A Vision Transformer with Low Complexity Self Attention for Edge Device

arXiv: https://arxiv.org/abs/2502.05800 · HTML: https://mlsanity.com/paper/2502.05800/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 28 references that are in the map.
- First posted on arXiv 9 Feb 2025.

## Builds on (most cited first, 19 of 19)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [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)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [Separable Self-attention for Mobile Vision Transformers](https://mlsanity.com/paper/2206.02680/) (2022)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications](https://mlsanity.com/paper/2206.10589/) (2022)
- [Rethinking Vision Transformers for MobileNet Size and Speed](https://mlsanity.com/paper/2212.08059/) (2022)
- [MobileOne: An Improved One millisecond Mobile Backbone](https://mlsanity.com/paper/2206.04040/) (2022)
- [SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design](https://mlsanity.com/paper/2401.16456/) (2024)

## Built on by (most cited first, 8 of 8)

- [FaceLiVT: Face Recognition using Linear Vision Transformer with Structural Reparameterization For Mobile Device](https://mlsanity.com/paper/2506.10361/) (2025)
- [Hyb-KAN ViT: Hybrid Kolmogorov-Arnold Networks Augmented Vision Transformer](https://mlsanity.com/paper/2505.04740/) (2025)
- [I-Segmenter: Integer-Only Vision Transformer for Efficient Semantic Segmentation](https://mlsanity.com/paper/2509.10334/) (2025)
- [Focus Your Attention: Towards Data-Intuitive Lightweight Vision Transformers](https://mlsanity.com/paper/2506.18791/) (2025)
- [CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer](https://mlsanity.com/paper/2511.14111/) (2025)
- [HAViT: Historical Attention Vision Transformer](https://mlsanity.com/paper/2603.18585/) (2026)
- [MicroViTv2: Beyond the FLOPS for Edge Energy-Friendly Vision Transformers](https://mlsanity.com/paper/2605.10148/) (2026)
- [CoDAT: Collaborative Dual-Attention Transformer with Low-Cost Temporal Modeling for Efficient Edge Action Recognition](https://mlsanity.com/paper/2608.06691/) (2026)

## Abstract (arXiv)

The Vision Transformer (ViT) has demonstrated state-of-the-art performance in various computer vision tasks, but its high computational demands make it impractical for edge devices with limited resources. This paper presents MicroViT, a lightweight Vision Transformer architecture optimized for edge devices by significantly reducing computational complexity while maintaining high accuracy. The core of MicroViT is the Efficient Single Head Attention (ESHA) mechanism, which utilizes group convolution to reduce feature redundancy and processes only a fraction of the channels, thus lowering the burden of the self-attention mechanism. MicroViT is designed using a multi-stage MetaFormer architecture, stacking multiple MicroViT encoders to enhance efficiency and performance. Comprehensive experiments on the ImageNet-1K and COCO datasets demonstrate that MicroViT achieves competitive accuracy while significantly improving 3.6 faster inference speed and reducing energy consumption with 40% higher efficiency than the MobileViT series, making it suitable for deployment in resource-constrained environments such as mobile and edge devices.