Efficient Track Anything

[📕Project][🤗Gradio Demo][📕Paper]

The Efficient Track Anything Model(EfficientTAM) takes a vanilla lightweight ViT image encoder. An efficient memory cross-attention is proposed to further improve the efficiency. Our EfficientTAMs are trained on SA-1B (image) and SA-V (video) datasets. EfficientTAM achieves comparable performance with SAM 2 with improved efficiency. Our EfficientTAM can run >10 frames per second with reasonable video segmentation performance on iPhone 15. Try our demo with a family of EfficientTAMs at [🤗Gradio Demo].

News

[Dec.4 2024] 🤗Efficient Track Anything for segment everything. Thanks to @SkalskiP!

[Dec.2 2024] We release the codebase of Efficient Track Anything.

Online Demo & Examples

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

EfficientTAM Video Segmentation Examples

SAM 2
EfficientTAM

EfficientTAM Image Segmentation Examples

Input Image, SAM, EficientSAM, SAM 2, EfficientTAM

Point-prompt
Box-prompt
Segment everything

Model

EfficientTAM checkpoints will be available soon on the Hugging Face Space.

Acknowledgement

• SAM2
• SAM2-Video-Predictor
• florence-sam
• SAM
• EfficientSAM

If you're using Efficient Track Anything in your research or applications, please cite using this BibTeX:

@article{xiong2024efficienttam,
  title={Efficient Track Anything},
  author={Yunyang Xiong, Chong Zhou, Xiaoyu Xiang, Lemeng Wu, Chenchen Zhu, Zechun Liu, Saksham Suri, Balakrishnan Varadarajan, Ramya Akula, Forrest Iandola, Raghuraman Krishnamoorthi, Bilge Soran, Vikas Chandra},
  journal={preprint arXiv:2411.18933},
  year={2024}
}