Faster Segment Anything(MobileSAM)

Official PyTorch Implementation of the .

MobileSAM performs on par with the original SAM (at least visually) and keeps exactly the same pipeline as the original SAM except for a change on the image encoder. Specifically, we replace the original heavyweight ViT-H encoder (632M) with a much smaller Tiny-ViT (5M). On a single GPU, MobileSAM runs around 12ms per image: 8ms on the image encoder and 4ms on the mask decoder.

• Github link
• Model Card link

License

The model is licensed under the Apache 2.0 license.

Acknowledgement

• Segment Anything provides the SA-1B dataset and the base codes.
• TinyViT provides codes and pre-trained models.

Citing MobileSAM

If you find this project useful for your research, please consider citing the following BibTeX entry.

@article{mobile_sam,
  title={Faster Segment Anything: Towards Lightweight SAM for Mobile Applications},
  author={Zhang, Chaoning and Han, Dongshen and Qiao, Yu and Kim, Jung Uk and Bae, Sung Ho and Lee, Seungkyu and Hong, Choong Seon},
  journal={arXiv preprint arXiv:2306.14289},
  year={2023}
}