Papers
arxiv:2306.14289

Faster Segment Anything: Towards Lightweight SAM for Mobile Applications

Published on Jun 25, 2023
· Featured in Daily Papers on Jun 27, 2023
Authors:
,
,
,

Abstract

Segment anything model (SAM) is a prompt-guided vision foundation model for cutting out the object of interest from its background. Since Meta research team released the SA project, SAM has attracted significant attention due to its impressive zero-shot transfer performance and high versatility of being compatible with other models for advanced vision applications like image editing with fine-grained control. Many of such use cases need to be run on resource-constraint edge devices, like mobile Apps. 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 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, MobileSAM runs around 10ms per image: 8ms on the image encoder and 2ms on the mask decoder. With superior performance and a higher versatility, our MobileSAM is 7 times smaller and 4 times faster than the concurrent FastSAM, making it more suitable for mobile applications. The code for MobileSAM project is provided at https://github.com/ChaoningZhang/MobileSAM

Community

Great paper, thank you for putting it together! One question I had was if there was an evaluation done with more data? From the paper, it looks like the mean IoU was calculated on only 200 samples, which is very small.

Sign up or log in to comment

Models citing this paper 2

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2306.14289 in a dataset README.md to link it from this page.

Spaces citing this paper 2

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.