# EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention

arXiv: https://arxiv.org/abs/2305.07027 · HTML: https://mlsanity.com/paper/2305.07027/

## Key facts

- Cited by 172 papers in the map (data through 14 Oct 2026).
- Builds on 69 of its 97 references that are in the map.
- First posted on arXiv 11 May 2023.

## Builds on (most cited first, 30 of 69)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [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)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [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)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [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)

## Built on by (most cited first, 30 of 172)

- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [Faster Segment Anything: Towards Lightweight SAM for Mobile Applications](https://mlsanity.com/paper/2306.14289/) (2023)
- [WonderWorld: Interactive 3D Scene Generation from a Single Image](https://mlsanity.com/paper/2406.09394/) (2024)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation](https://mlsanity.com/paper/2406.02918/) (2024)
- [EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba](https://mlsanity.com/paper/2403.09977/) (2024)
- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [Grounding DINO 1.5: Advance the "Edge" of Open-Set Object Detection](https://mlsanity.com/paper/2405.10300/) (2024)
- [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)
- [RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models](https://mlsanity.com/paper/2412.07679/) (2024)
- [SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design](https://mlsanity.com/paper/2401.16456/) (2024)
- [A Survey on Transformer Compression](https://mlsanity.com/paper/2402.05964/) (2024)
- [Frequency-Spatial Entanglement Learning for Camouflaged Object Detection](https://mlsanity.com/paper/2409.01686/) (2024)
- [Training-Free Efficient Video Generation via Dynamic Token Carving](https://mlsanity.com/paper/2505.16864/) (2025)
- [SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.10156/) (2024)
- [How Far Are We From AGI: Are LLMs All We Need?](https://mlsanity.com/paper/2405.10313/) (2024)
- [LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregation](https://mlsanity.com/paper/2406.19833/) (2024)
- [FwdLLM: Efficient FedLLM using Forward Gradient](https://mlsanity.com/paper/2308.13894/) (2023)
- [General surgery vision transformer: A video pre-trained foundation model for general surgery](https://mlsanity.com/paper/2403.05949/) (2024)
- [Scaling up self-supervised learning for improved surgical foundation models](https://mlsanity.com/paper/2501.09436/) (2025)
- [FlexiMo: A Flexible Remote Sensing Foundation Model](https://mlsanity.com/paper/2503.23844/) (2025)
- [LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstruction](https://mlsanity.com/paper/2406.16073/) (2024)
- [Efficient Track Anything](https://mlsanity.com/paper/2411.18933/) (2024)
- [From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape](https://mlsanity.com/paper/2312.10868/) (2023)
- [PanGu-π: Enhancing Language Model Architectures via Nonlinearity Compensation](https://mlsanity.com/paper/2312.17276/) (2023)
- [MLP Can Be A Good Transformer Learner](https://mlsanity.com/paper/2404.05657/) (2024)
- [EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality](https://mlsanity.com/paper/2411.15241/) (2024)
- [FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention](https://mlsanity.com/paper/2512.01540/) (2025)
- [MobileMamba: Lightweight Multi-Receptive Visual Mamba Network](https://mlsanity.com/paper/2411.15941/) (2024)

## Abstract (arXiv)

Vision transformers have shown great success due to their high model capabilities. However, their remarkable performance is accompanied by heavy computation costs, which makes them unsuitable for real-time applications. In this paper, we propose a family of high-speed vision transformers named EfficientViT. We find that the speed of existing transformer models is commonly bounded by memory inefficient operations, especially the tensor reshaping and element-wise functions in MHSA. Therefore, we design a new building block with a sandwich layout, i.e., using a single memory-bound MHSA between efficient FFN layers, which improves memory efficiency while enhancing channel communication. Moreover, we discover that the attention maps share high similarities across heads, leading to computational redundancy. To address this, we present a cascaded group attention module feeding attention heads with different splits of the full feature, which not only saves computation cost but also improves attention diversity. Comprehensive experiments demonstrate EfficientViT outperforms existing efficient models, striking a good trade-off between speed and accuracy. For instance, our EfficientViT-M5 surpasses MobileNetV3-Large by 1.9% in accuracy, while getting 40.4% and 45.2% higher throughput on Nvidia V100 GPU and Intel Xeon CPU, respectively. Compared to the recent efficient model MobileViT-XXS, EfficientViT-M2 achieves 1.8% superior accuracy, while running 5.8x/3.7x faster on the GPU/CPU, and 7.4x faster when converted to ONNX format. Code and models are available at https://github.com/microsoft/Cream/tree/main/EfficientViT.