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.
[AAAI 2024] AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model
| Date | Stars |
|---|---|
| 2026-07-31 | 325 |
| 2026-08-04 | 325 |
| 2026-08-06 | 325 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model (AAAI 2024) <!-- <br> --> [Teng Hu<sup>1#</sup>](https://sjtuplayer.github.io/), [Jiangning Zhang<sup>2#</sup>](https://zhangzjn.github.io/), [Ran Yi<sup>1*</sup>](https://yiranran.github.io/), [Yuzhen Du<sup>1</sup>](https://github.com/YuzhenD), [Xu Chen<sup>2</sup>](https://scholar.google.com/citations?hl=zh-CN&user=1621dVIAAAAJ), [Liang Liu<sup>2</sup>](https://scholar.google.com/citations?hl=zh-CN&user=Kkg3IPMAAAAJ), [Yabiao Wang<sup>2</sup>](https://scholar.google.com/citations?hl=zh-CN&user=xiK4nFUAAAAJ), and [Chengjie Wang<sup>1,2</sup>](https://scholar.google.com/citations?hl=zh-CN&user=fqte5H4AAAAJ). <!-- <br> --> (#Equal contribution,*Corresponding author) [<sup>1</sup>Shanghai Jiao Tong University](https://www.sjtu.edu.cn/), [<sup>2</sup>Youtu Lab, Tencent](https://open.youtu.qq.com/#/open) [](https://arxiv.org/abs/2312.05767) [Project Page](https://sjtuplayer.github.io/anomalydiffusion-page/) ## News **June 29, 2024** - The anomalous data for hazelnut has been updated since the previous version can only achieve AP<85. Current Version can achieve an AP score around 96. You can download the new version in the following link to Google Drive. - ```ldm/models/diffusion/ddpm.py``` has been updated since previous validation step has some problem. But it does not influence the training results. ## Todo (Latest update: 2024/08/11) - [x] **Release the training code - [x] **Release the UNet checkpoints for testing anomaly detection accuracy - [x] **Release the data - [x] **Release checkpoints for anomalydiffusion. - [x] **Release the inference code - [x] **Release the code for ic-lpipis ## Data and checkpoints The generated anomaly data and all the checkpoints can be downloaded from the following links. And some checkpoints should be placed at the corresponding directory. (Note that we have filtered out some data with poor generation effects. Therefore, some classes have relatively fewer samples.) [//]: # (You can download the checkpoints for the UNet models trained on the generated data from ) [//]: # ([Google Drive](https://drive.google.com/drive/folders/1kcOdfQrvWeJyliGTYJ4HXKU5ccfn7t96?usp=sharing)) [//]: # (or [百度网盘](https://pan.baidu.com/s/1Xoe__ODeq_YrVc9lA-7B_A) (提取码: 0306).) [//]: # (| | Google Drive | 百度网盘 |) [//]: # (|------------------------------------------|--------------|----------|) [//]: # (| Generated data | [Google Drive](https://drive.google.com/file/d/1yzsZdW_xS-v4GprE2KQmQ1EbIWyGyFcG/view?usp=sharing) | [百度网盘](https://pan.baidu.com/s/12gKMfc64sy3JDx5FAR-ytQ) (提取码: 0306) |) [//]: # (| Checkpoints for anomaly generation model | | |) [//]: # (| Checkpoints for mask generation model | | |) [//]: # (| Checkpoints for anomaly localization | [Google Drive](https://drive.google.com/drive/folders/1kcOdfQrvWeJyliGTYJ4HXKU5ccfn7t96?usp=sharing) | [百度网盘](https://pan.baidu.com/s/1Xoe__ODeq_YrVc9lA-7B_A) (提取码: 0306) |) [//]: # (| Checkpoints for anomaly classification | | |) | Data and Models | Download | Place at | |------------------------------------------|------------------------------------------------------------------------------------------------------|---------------------------| | Generated data | [Google Drive](https://drive.google.com/file/d/1fV2S-Memcll0oAnrPmfNLgi8E7yb7XTC/view?usp=drive_link) | $path_to_the_generated_data | | Checkpoints for anomaly generation model | [Google Drive](https://drive.google.co
Excerpt of 8,328 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:3f5075ea7f279cc6, desc:image generation, desc:diffusion model