EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
[Dec.6 2023] EfficientSAM demo is available on the HuggingFace Space (huge thanks to all the HF team for their support).
[Dec.5 2023] We release the torchscript version of EfficientSAM and share a colab.
Online demo and examples can be found in the project page.
| Point-prompt |  |
| Box-prompt |  |
| Segment everything |  |
| Saliency |  |
Models for GPU/CPU are available at the file folder of HuggingFace Space.
| EfficientSAM-S | EfficientSAM-Ti |
|---|---|
| Download | Download |
You can directly use EfficientSAM,
import torch
efficientsam = torch.jit.load(efficientsam_s_gpu.jit)
The colab is shared here
If you're using EfficientSAM in your research or applications, please cite using this BibTeX:
@article{xiong2023efficientsam,
title={EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything},
author={Yunyang Xiong, Bala Varadarajan, Lemeng Wu, Xiaoyu Xiang, Fanyi Xiao, Chenchen Zhu, Xiaoliang Dai, Dilin Wang, Fei Sun, Forrest Iandola, Raghuraman Krishnamoorthi, Vikas Chandra},
journal={arXiv:2312.00863},
year={2023}
}