# Faster Segment Anything: Towards Lightweight SAM for Mobile Applications

arXiv: https://arxiv.org/abs/2306.14289 · HTML: https://mlsanity.com/paper/2306.14289/

## Key facts

- Cited by 352 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 41 references that are in the map.
- First posted on arXiv 25 Jun 2023.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (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)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Fast Segment Anything](https://mlsanity.com/paper/2306.12156/) (2023)
- [EfficientFormer: Vision Transformers at MobileNet Speed](https://mlsanity.com/paper/2206.01191/) (2022)
- [TinyViT: Fast Pretraining Distillation for Small Vision Transformers](https://mlsanity.com/paper/2207.10666/) (2022)
- [Track Anything: Segment Anything Meets Videos](https://mlsanity.com/paper/2304.11968/) (2023)
- [Inpaint Anything: Segment Anything Meets Image Inpainting](https://mlsanity.com/paper/2304.06790/) (2023)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [Can SAM Segment Anything? When SAM Meets Camouflaged Object Detection](https://mlsanity.com/paper/2304.04709/) (2023)
- [Anything-3D: Towards Single-view Anything Reconstruction in the Wild](https://mlsanity.com/paper/2304.10261/) (2023)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [How Does SimSiam Avoid Collapse Without Negative Samples? A Unified Understanding with Self-supervised Contrastive Learning](https://mlsanity.com/paper/2203.16262/) (2022)
- [Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios](https://mlsanity.com/paper/2207.05501/) (2022)
- [Input Augmentation with SAM: Boosting Medical Image Segmentation with Segmentation Foundation Model](https://mlsanity.com/paper/2304.11332/) (2023)
- [One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era](https://mlsanity.com/paper/2304.06488/) (2023)
- [Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo](https://mlsanity.com/paper/2203.17248/) (2022)

## Built on by (most cited first, 30 of 352)

- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023)
- [VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation](https://mlsanity.com/paper/2312.03275/) (2023)
- [Tracking Anything with Decoupled Video Segmentation](https://mlsanity.com/paper/2309.03903/) (2023)
- [EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything](https://mlsanity.com/paper/2312.00863/) (2023)
- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation](https://mlsanity.com/paper/2311.15707/) (2023)
- [SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding](https://mlsanity.com/paper/2310.15308/) (2023)
- [Foundational Models Defining a New Era in Vision: A Survey and Outlook](https://mlsanity.com/paper/2307.13721/) (2023)
- [General In-Hand Object Rotation with Vision and Touch](https://mlsanity.com/paper/2309.09979/) (2023)
- [Segment Anything Meets Point Tracking](https://mlsanity.com/paper/2307.01197/) (2023)
- [Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively](https://mlsanity.com/paper/2401.02955/) (2024)
- [EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model](https://mlsanity.com/paper/2406.20076/) (2024)
- [Real-World Robot Applications of Foundation Models: A Review](https://mlsanity.com/paper/2402.05741/) (2024)
- [SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More](https://mlsanity.com/paper/2408.04579/) (2024)
- [Adapting Segment Anything Model for Change Detection in HR Remote Sensing Images](https://mlsanity.com/paper/2309.01429/) (2023)
- [Watermark Anything with Localized Messages](https://mlsanity.com/paper/2411.07231/) (2024)
- [LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning](https://mlsanity.com/paper/2404.08767/) (2024)
- [Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos](https://mlsanity.com/paper/2506.05302/) (2025)
- [VCP-CLIP: A visual context prompting model for zero-shot anomaly segmentation](https://mlsanity.com/paper/2407.12276/) (2024)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models](https://mlsanity.com/paper/2407.00983/) (2024)
- [DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion](https://mlsanity.com/paper/2407.12899/) (2024)
- [IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection](https://mlsanity.com/paper/2407.07520/) (2024)
- [SAMPro3D: Locating SAM Prompts in 3D for Zero-Shot Instance Segmentation](https://mlsanity.com/paper/2311.17707/) (2023)
- [MobileSAMv2: Faster Segment Anything to Everything](https://mlsanity.com/paper/2312.09579/) (2023)
- [EdgeSAM: Prompt-In-the-Loop Distillation for SAM](https://mlsanity.com/paper/2312.06660/) (2023)
- [Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model](https://mlsanity.com/paper/2404.01862/) (2024)
- [CorrCLIP: Reconstructing Patch Correlations in CLIP for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2411.10086/) (2024)
- [TinySAM: Pushing the Envelope for Efficient Segment Anything Model](https://mlsanity.com/paper/2312.13789/) (2023)

## Abstract (arXiv)

Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like image editing with fine-grained control). Many of such applications need to be run on resource-constraint edge devices, like mobile phones. In this work, we aim to make SAM mobile-friendly by replacing the heavyweight image encoder with a lightweight one. A naive way to train such a new SAM as in the original SAM paper leads to unsatisfactory performance, especially when limited training sources are available. We find that this is mainly caused by the coupled optimization of the image encoder and mask decoder, motivated by which we propose decoupled distillation. Concretely, we distill the knowledge from the heavy image encoder (ViT-H in the original SAM) to a lightweight image encoder, which can be automatically compatible with the mask decoder in the original SAM. The training can be completed on a single GPU within less than one day, and the resulting lightweight SAM is termed MobileSAM which is more than 60 times smaller yet performs on par with the original SAM. For inference speed, With a single GPU, MobileSAM runs around 10ms per image: 8ms on the image encoder and 4ms on the mask decoder. With superior performance, our MobileSAM is around 5 times faster than the concurrent FastSAM and 7 times smaller, making it more suitable for mobile applications. Moreover, we show that MobileSAM can run relatively smoothly on CPU. The code for our project is provided at hrefhttps://github.com/ChaoningZhang/MobileSAMtextcolorredMobileSAM), with a demo showing that MobileSAM can run relatively smoothly on CPU.