# Rethinking Vision Transformers for MobileNet Size and Speed

arXiv: https://arxiv.org/abs/2212.08059 · HTML: https://mlsanity.com/paper/2212.08059/

## Key facts

- Cited by 121 papers in the map (data through 14 Oct 2026).
- Builds on 78 of its 92 references that are in the map.
- First posted on arXiv 15 Dec 2022.

## Builds on (most cited first, 30 of 78)

- [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)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [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)
- [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)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [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)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification](https://mlsanity.com/paper/2106.02034/) (2021)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Panoptic Feature Pyramid Networks](https://mlsanity.com/paper/1901.02446/) (2019)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [CoAtNet: Marrying Convolution and Attention for All Data Sizes](https://mlsanity.com/paper/2106.04803/) (2021)

## Built on by (most cited first, 30 of 121)

- [SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds](https://mlsanity.com/paper/2306.00980/) (2023)
- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [MobileNetV4 -- Universal Models for the Mobile Ecosystem](https://mlsanity.com/paper/2404.10518/) (2024)
- [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training](https://mlsanity.com/paper/2311.17049/) (2023)
- [Efficient Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2405.10739/) (2024)
- [TransNeXt: Robust Foveal Visual Perception for Vision Transformers](https://mlsanity.com/paper/2311.17132/) (2023)
- [SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design](https://mlsanity.com/paper/2401.16456/) (2024)
- [Adaptive Frequency Filters As Efficient Global Token Mixers](https://mlsanity.com/paper/2307.14008/) (2023)
- [A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking](https://mlsanity.com/paper/2309.02031/) (2023)
- [PEM: Prototype-based Efficient MaskFormer for Image Segmentation](https://mlsanity.com/paper/2402.19422/) (2024)
- [MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications](https://mlsanity.com/paper/2307.00395/) (2023)
- [SegMAN: Omni-scale Context Modeling with State Space Models and Local Attention for Semantic Segmentation](https://mlsanity.com/paper/2412.11890/) (2024)
- [Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation](https://mlsanity.com/paper/2405.06228/) (2024)
- [Learnable Ophthalmology SAM](https://mlsanity.com/paper/2304.13425/) (2023)
- [GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs](https://mlsanity.com/paper/2405.06849/) (2024)
- [Spiking Vision Transformer with Saccadic Attention](https://mlsanity.com/paper/2502.12677/) (2025)
- [SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition](https://mlsanity.com/paper/2301.13156/) (2023)
- [EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality](https://mlsanity.com/paper/2411.15241/) (2024)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)
- [Efficient Modulation for Vision Networks](https://mlsanity.com/paper/2403.19963/) (2024)
- [The 3D-PC: a benchmark for visual perspective taking in humans and machines](https://mlsanity.com/paper/2406.04138/) (2024)
- [On Efficient Variants of Segment Anything Model: A Survey](https://mlsanity.com/paper/2410.04960/) (2024)
- [MobileMamba: Lightweight Multi-Receptive Visual Mamba Network](https://mlsanity.com/paper/2411.15941/) (2024)
- [TinyViM: Frequency Decoupling for Tiny Hybrid Vision Mamba](https://mlsanity.com/paper/2411.17473/) (2024)
- [UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery](https://mlsanity.com/paper/2501.01855/) (2025)
- [LSNet: See Large, Focus Small](https://mlsanity.com/paper/2503.23135/) (2025)
- [CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications](https://mlsanity.com/paper/2408.03703/) (2024)
- [RigNet++: Semantic Assisted Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2309.00655/) (2023)
- [Efficient Low-rank Backpropagation for Vision Transformer Adaptation](https://mlsanity.com/paper/2309.15275/) (2023)
- [LWGANet: Addressing Spatial and Channel Redundancy in Remote Sensing Visual Tasks with Light-Weight Grouped Attention](https://mlsanity.com/paper/2501.10040/) (2025)

## Abstract (arXiv)

With the success of Vision Transformers (ViTs) in computer vision tasks, recent arts try to optimize the performance and complexity of ViTs to enable efficient deployment on mobile devices. Multiple approaches are proposed to accelerate attention mechanism, improve inefficient designs, or incorporate mobile-friendly lightweight convolutions to form hybrid architectures. However, ViT and its variants still have higher latency or considerably more parameters than lightweight CNNs, even true for the years-old MobileNet. In practice, latency and size are both crucial for efficient deployment on resource-constraint hardware. In this work, we investigate a central question, can transformer models run as fast as MobileNet and maintain a similar size? We revisit the design choices of ViTs and propose a novel supernet with low latency and high parameter efficiency. We further introduce a novel fine-grained joint search strategy for transformer models that can find efficient architectures by optimizing latency and number of parameters simultaneously. The proposed models, EfficientFormerV2, achieve 3.5% higher top-1 accuracy than MobileNetV2 on ImageNet-1K with similar latency and parameters. This work demonstrate that properly designed and optimized vision transformers can achieve high performance even with MobileNet-level size and speed.