# EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers

arXiv: https://arxiv.org/abs/2205.03436 · HTML: https://mlsanity.com/paper/2205.03436/

## Key facts

- Cited by 116 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 66 references that are in the map.
- First posted on arXiv 6 May 2022.

## Builds on (most cited first, 30 of 61)

- [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)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [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)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [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)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [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)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [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)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)

## Built on by (most cited first, 30 of 116)

- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One](https://mlsanity.com/paper/2312.06709/) (2023)
- [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)
- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [Rethinking Vision Transformers for MobileNet Size and Speed](https://mlsanity.com/paper/2212.08059/) (2022)
- [Global Context Vision Transformers](https://mlsanity.com/paper/2206.09959/) (2022)
- [RMT: Retentive Networks Meet Vision Transformers](https://mlsanity.com/paper/2309.11523/) (2023)
- [SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications](https://mlsanity.com/paper/2303.15446/) (2023)
- [FasterViT: Fast Vision Transformers with Hierarchical Attention](https://mlsanity.com/paper/2306.06189/) (2023)
- [Omni Aggregation Networks for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2304.10244/) (2023)
- [Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2304.10410/) (2023)
- [SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design](https://mlsanity.com/paper/2401.16456/) (2024)
- [Rewrite the Stars](https://mlsanity.com/paper/2403.19967/) (2024)
- [EdgeSAM: Prompt-In-the-Loop Distillation for SAM](https://mlsanity.com/paper/2312.06660/) (2023)
- [Rethinking Mobile Block for Efficient Attention-based Models](https://mlsanity.com/paper/2301.01146/) (2023)
- [MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications](https://mlsanity.com/paper/2307.00395/) (2023)
- [Dynamic Perceiver for Efficient Visual Recognition](https://mlsanity.com/paper/2306.11248/) (2023)
- [A Closer Look at Self-Supervised Lightweight Vision Transformers](https://mlsanity.com/paper/2205.14443/) (2022)
- [Dual Vision Transformer](https://mlsanity.com/paper/2207.04976/) (2022)
- [Lightweight Vision Transformer with Bidirectional Interaction](https://mlsanity.com/paper/2306.00396/) (2023)
- [TinyMIM: An Empirical Study of Distilling MIM Pre-trained Models](https://mlsanity.com/paper/2301.01296/) (2023)
- [Skip-Attention: Improving Vision Transformers by Paying Less Attention](https://mlsanity.com/paper/2301.02240/) (2023)
- [RGB no more: Minimally-decoded JPEG Vision Transformers](https://mlsanity.com/paper/2211.16421/) (2022)
- [Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model](https://mlsanity.com/paper/2406.19369/) (2024)
- [EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality](https://mlsanity.com/paper/2411.15241/) (2024)
- [Achelous: A Fast Unified Water-surface Panoptic Perception Framework based on Fusion of Monocular Camera and 4D mmWave Radar](https://mlsanity.com/paper/2307.07102/) (2023)
- [Efficient Modulation for Vision Networks](https://mlsanity.com/paper/2403.19963/) (2024)
- [MobileMamba: Lightweight Multi-Receptive Visual Mamba Network](https://mlsanity.com/paper/2411.15941/) (2024)
- [GroupMamba: Efficient Group-Based Visual State Space Model](https://mlsanity.com/paper/2407.13772/) (2024)

## Abstract (arXiv)

Self-attention based models such as vision transformers (ViTs) have emerged as a very competitive architecture alternative to convolutional neural networks (CNNs) in computer vision. Despite increasingly stronger variants with ever-higher recognition accuracies, due to the quadratic complexity of self-attention, existing ViTs are typically demanding in computation and model size. Although several successful design choices (e.g., the convolutions and hierarchical multi-stage structure) of prior CNNs have been reintroduced into recent ViTs, they are still not sufficient to meet the limited resource requirements of mobile devices. This motivates a very recent attempt to develop light ViTs based on the state-of-the-art MobileNet-v2, but still leaves a performance gap behind. In this work, pushing further along this under-studied direction we introduce EdgeViTs, a new family of light-weight ViTs that, for the first time, enable attention-based vision models to compete with the best light-weight CNNs in the tradeoff between accuracy and on-device efficiency. This is realized by introducing a highly cost-effective local-global-local (LGL) information exchange bottleneck based on optimal integration of self-attention and convolutions. For device-dedicated evaluation, rather than relying on inaccurate proxies like the number of FLOPs or parameters, we adopt a practical approach of focusing directly on on-device latency and, for the first time, energy efficiency. Specifically, we show that our models are Pareto-optimal when both accuracy-latency and accuracy-energy trade-offs are considered, achieving strict dominance over other ViTs in almost all cases and competing with the most efficient CNNs. Code is available at https://github.com/saic-fi/edgevit.