# Efficient Track Anything
[[`📕Project`](https://yformer.github.io/efficient-track-anything/)][[`🤗Gradio Demo`](https://2ab5e2198a0dcbe8a2.gradio.live)][[`📕Paper`](https://arxiv.org/pdf/2411.18933)]
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`](https://2ab5e2198a0dcbe8a2.gradio.live)].
## News
[Dec.4 2024] [`🤗Efficient Track Anything for segment everything`](https://5239f8e221db7ee8a0.gradio.live/). 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](https://yformer.github.io/efficient-track-anything/).
## 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](https://huggingface.co/spaces/yunyangx/EfficientTAM/tree/main).
## Acknowledgement
+ [SAM2](https://github.com/facebookresearch/sam2)
+ [SAM2-Video-Predictor](https://huggingface.co/spaces/fffiloni/SAM2-Video-Predictor)
+ [florence-sam](https://huggingface.co/spaces/SkalskiP/florence-sam)
+ [SAM](https://github.com/facebookresearch/segment-anything)
+ [EfficientSAM](https://github.com/yformer/EfficientSAM)
If you're using Efficient Track Anything in your research or applications, please cite using this BibTeX:
```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}
}
```
Raw data
{
"_id": null,
"home_page": "https://yformer.github.io/efficient-track-anything/",
"name": "efficient-track-anything",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10.0",
"maintainer_email": null,
"keywords": null,
"author": "Meta AI",
"author_email": "yunyang@meta.com",
"download_url": "https://files.pythonhosted.org/packages/60/bb/f50d651bcc76604fc0f8de85038e8ab266b7a987d63c521ad07b438c9091/efficient_track_anything-1.0.tar.gz",
"platform": null,
"description": "# Efficient Track Anything\n[[`\ud83d\udcd5Project`](https://yformer.github.io/efficient-track-anything/)][[`\ud83e\udd17Gradio Demo`](https://2ab5e2198a0dcbe8a2.gradio.live)][[`\ud83d\udcd5Paper`](https://arxiv.org/pdf/2411.18933)]\n\n\n\nThe **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 [[`\ud83e\udd17Gradio Demo`](https://2ab5e2198a0dcbe8a2.gradio.live)].\n\n\n\n## News\n[Dec.4 2024] [`\ud83e\udd17Efficient Track Anything for segment everything`](https://5239f8e221db7ee8a0.gradio.live/). Thanks to @SkalskiP!\n\n[Dec.2 2024] We release the codebase of Efficient Track Anything.\n\n## Online Demo & Examples\nOnline demo and examples can be found in the [project page](https://yformer.github.io/efficient-track-anything/).\n\n## EfficientTAM Video Segmentation Examples\n | | |\n:-------------------------:|:-------------------------:\nSAM 2 | \nEfficientTAM | \n\n## EfficientTAM Image Segmentation Examples\nInput Image, SAM, EficientSAM, SAM 2, EfficientTAM\n | | |\n:-------------------------:|:-------------------------:\nPoint-prompt | \nBox-prompt | \nSegment everything |\n\n## Model\nEfficientTAM checkpoints will be available soon on the [Hugging Face Space](https://huggingface.co/spaces/yunyangx/EfficientTAM/tree/main).\n\n## Acknowledgement\n\n+ [SAM2](https://github.com/facebookresearch/sam2)\n+ [SAM2-Video-Predictor](https://huggingface.co/spaces/fffiloni/SAM2-Video-Predictor)\n+ [florence-sam](https://huggingface.co/spaces/SkalskiP/florence-sam)\n+ [SAM](https://github.com/facebookresearch/segment-anything)\n+ [EfficientSAM](https://github.com/yformer/EfficientSAM)\n\nIf you're using Efficient Track Anything in your research or applications, please cite using this BibTeX:\n```bibtex\n\n\n@article{xiong2024efficienttam,\n title={Efficient Track Anything},\n 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},\n journal={preprint arXiv:2411.18933},\n year={2024}\n}\n```\n",
"bugtrack_url": null,
"license": "Apache 2.0",
"summary": "Efficient Track Anything",
"version": "1.0",
"project_urls": {
"Homepage": "https://yformer.github.io/efficient-track-anything/"
},
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "4792d291086fc97c9e5abe45d706ea1467037b51ef7bea6feda4717c535a6447",
"md5": "2b1b1c9d05e8f63cb16e6f8e1e3dd3b5",
"sha256": "b4df95d0f093437fa521778bf6b740b6644dbd0b7741f7c023c23c57f053103e"
},
"downloads": -1,
"filename": "efficient_track_anything-1.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "2b1b1c9d05e8f63cb16e6f8e1e3dd3b5",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10.0",
"size": 77604,
"upload_time": "2024-12-12T22:08:44",
"upload_time_iso_8601": "2024-12-12T22:08:44.925852Z",
"url": "https://files.pythonhosted.org/packages/47/92/d291086fc97c9e5abe45d706ea1467037b51ef7bea6feda4717c535a6447/efficient_track_anything-1.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "60bbf50d651bcc76604fc0f8de85038e8ab266b7a987d63c521ad07b438c9091",
"md5": "633304cade3705a4f30ea66e011ed9b3",
"sha256": "b89f919d3085337390000d850a416e40e5b6ec2341544fc9c02e1582aa282be7"
},
"downloads": -1,
"filename": "efficient_track_anything-1.0.tar.gz",
"has_sig": false,
"md5_digest": "633304cade3705a4f30ea66e011ed9b3",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10.0",
"size": 66539,
"upload_time": "2024-12-12T22:08:47",
"upload_time_iso_8601": "2024-12-12T22:08:47.647972Z",
"url": "https://files.pythonhosted.org/packages/60/bb/f50d651bcc76604fc0f8de85038e8ab266b7a987d63c521ad07b438c9091/efficient_track_anything-1.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-12 22:08:47",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "efficient-track-anything"
}
JSON