Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
(CVPR 2022) Pytorch implementation of "Self-supervised transformers for unsupervised object discovery using normalized cut"
| Date | Stars |
|---|---|
| 2026-07-24 | 339 |
| 2026-07-25 | 339 |
| 2026-07-28 | 339 |
| 2026-07-30 | 339 |
| 2026-08-06 | 339 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# (CVPR 2022) TokenCut
Pytorch implementation of **Tokencut**:
**Self-supervised Transformers for Unsupervised Object Discovery using Normalized Cut**
*[Yangtao Wang](https://yangtaowang95.github.io), [Xi Shen](https://xishen0220.github.io/), [Shell Xu Hu](http://hushell.github.io/), [Yuan Yuan](https://yyuanad.github.io/), [James L. Crowley](http://crowley-coutaz.fr/jlc/jlc.html), [Dominique Vaufreydaz](https://research.vaufreydaz.org/)*
[[Project page](https://www.m-psi.fr/Papers/TokenCut2022/)]
[[ Github (Video Segmentation) ](https://github.com/YangtaoWANG95/TokenCut_video)]
[[Paper](https://arxiv.org/pdf/2202.11539.pdf)]
[](https://colab.research.google.com/github/YangtaoWANG95/TokenCut/blob/master/inference_demo.ipynb)
[](https://huggingface.co/spaces/yangtaowang/TokenCut)
<p align="center">
<img width="100%" alt="TokenCut teaser" src="examples/overview.png">
</p>
If our project is helpful for your research, please consider citing :
```
@inproceedings{wang2022tokencut,
title={Self-supervised Transformers for Unsupervised Object Discovery using Normalized Cut},
author={Wang, Yangtao and Shen, Xi and Hu, Shell Xu and Yuan, Yuan and Crowley, James L. and Vaufreydaz, Dominique},
booktitle={Conference on Computer Vision and Pattern Recognition}
year={2022}
}
```
## Table of Content
* [1. Updates](#1-updates)
* [2. Installation](#2-installation)
* [2.1 Dependencies](#21-dependencies)
* [2.2 Data](#22-data)
* [3. Quick Start](#3-quick-start)
* [3.1 Detecting an object in one image](#31-detecting-an-object-in-one-image)
* [3.2 Segmenting a salient region in one image](#32-segmenting-a-salient-region-in-one-image)
* [4. Evaluation](#4-evaluation)
* [4.1 Unsupervised object discovery](#41-unsupervised-object-discovery)
* [4.2 Unsupervised saliency detection](#42-unsupervised-saliency-detection)
* [4.3 Weakly supervised object detection](#43-weakly-supervised-object-detection)
* [5. Acknowledgement](#5-acknowledgement)
## 1. Updates
***09/06/2022***
Extension work of [TokeCut Video Segmentation](https://github.com/YangtaoWANG95/TokenCut_video) is realised!
***03/10/2022***
Creating a 480p Demo using [Gradio](https://github.com/gradio-app/gradio). Try out the Web Demo: [](https://huggingface.co/spaces/yangtaowang/TokenCut)
Internet image results:
<p >
<img width="20%" alt="TokenCut visualizations" src="examples/internet_image/kungfu_pred.jpg">
<img width="20%" alt="TokenCut visualizations" src="examples/internet_image/kungfu_attn.jpg">
<img width="19%" alt="TokenCut visualizations" src="examples/internet_image/pokemon_pred.jpg">
<img width="19.5%" alt="TokenCut visualizations" src="examples/internet_image/pokemon_attn.jpg">
</p>
***02/26/2022***
Integrated into [Huggingface Spaces 🤗](https://huggingface.co/spaces) using [Gradio](https://github.com/gradio-app/gradio). Try out the Web Demo: [](https://huggingface.co/spaces/akhaliq/TokenCut)
***02/26/2022***
A simple TokenCut Colab Demo is available.
***02/21/2022***
Initial commit: Code of TokenCut is released, including evaluation of unsupervised object discovery, unsupervised saliency object detection, weakly supervised object locolization.
## 2. Installation
### 2.1 Dependencies
This code was implemented with Python 3.7, PyTorch 1.7.1 and CUDA 11.2. Please refer to [the official installation](https://pytorch.org/get-started/previous-versions/). If CUDA 10.2 has been properly installed :
```
pip install torch==1.7.1 torchvision==0.8.2
```
In order to install the additionnal dependencies, please launch the following command:
```
pip install Excerpt of 11,015 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9ee323efdb4d82f4, topic:transformer