robertknight / EfficientSAM

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

EfficientSAM

EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything

News

[Dec.11 2023] The model code is fully available in this repository. The sample_inference binary shows how to instantiate the model and query points on an image.

[Dec.6 2023] EfficientSAM demo is available on the Hugging Face 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 & Examples

Online demo and examples can be found in the project page.

EfficientSAM Instance Segmentation Examples

Point-prompt
Box-prompt
Segment everything
Saliency

Model

Models for GPU/CPU are available at the file folder of Hugging Face Space.

EfficientSAM-S	EfficientSAM-Ti
Download	Download

You can directly use EfficientSAM,

import torch

efficientsam = torch.jit.load(efficientsam_s_gpu.jit)

Colab

The colab is shared here

Acknowledgement

• SAM
• MobileSAM
• FastSAM
• U-2-Net

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}
}