FantasticGNU
/

AnomalyGPT

English

Chinese

Model card Files Files and versions

xet

Community

FantasticGNU commited on Aug 29, 2023

Commit

609c6e3

1 Parent(s): 711130e

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -1,6 +1,6 @@
 # AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models
-![License](https://img.shields.io/badge/Code%20License-Apache_2.0-green.svg)
 <p align="left">
    🌐 <a href="https://anomalygpt.github.io" target="_blank">Project Page</a> • 🤗 <a href="" target="_blank">Online Demo</a> • 📃 <a href="" target="_blank">Paper</a> • 🤖 <a href="https://huggingface.co/FantasticGNU/AnomalyGPT" target="_blank">Model</a> • 📹 <a href="https://www.youtube.com/watch?v=lcxBfy0YnNA" target="_blank">Video</a>
@@ -43,11 +43,11 @@ Zhaopeng Gu, Bingke Zhu, Guibo Zhu, Yingying Chen, Ming Tang, Jinqiao Wang
-![](images/compare.png)
 **AnomalyGPT** is the first Large Vision-Language Model (LVLM) based Industrial Anomaly Detection (IAD) method that can detect anomalies in industrial images without the need for manually specified thresholds. Existing IAD methods can only provide anomaly scores and need manually threshold setting, while existing LVLMs cannot detect anomalies in the image. AnomalyGPT can not only indicate the presence and location of anomaly but also provide information about the image.
-![](images/AnomalyGPT.png)
 We leverage a pre-trained image encoder and a Large Language Model (LLM) to align IAD images and their corresponding textual descriptions via simulated anomaly data. We employ a lightweight, visual-textual feature-matching-based image decoder to obtain localization result, and design a prompt learner to provide fine-grained semantic to LLM and fine-tune the LVLM using prompt embeddings. Our method can also detect anomalies for previously unseen items with few normal sample provided.
@@ -243,7 +243,7 @@ Note that the epoch number can be set in the `epochs` argument at [./code/config
 ### License
-AnomalyGPT is licensed under the [Apache 2.0 license](./LICENSE).
 ****

 # AnomalyGPT: Detecting Industrial Anomalies using Large Vision-Language Models
+![License](https://img.shields.io/badge/License-CC%20BY%20NC%20SA%204.0-red.svg)
 <p align="left">
    🌐 <a href="https://anomalygpt.github.io" target="_blank">Project Page</a> • 🤗 <a href="" target="_blank">Online Demo</a> • 📃 <a href="" target="_blank">Paper</a> • 🤖 <a href="https://huggingface.co/FantasticGNU/AnomalyGPT" target="_blank">Model</a> • 📹 <a href="https://www.youtube.com/watch?v=lcxBfy0YnNA" target="_blank">Video</a>
+!()[./images/compare.png]
 **AnomalyGPT** is the first Large Vision-Language Model (LVLM) based Industrial Anomaly Detection (IAD) method that can detect anomalies in industrial images without the need for manually specified thresholds. Existing IAD methods can only provide anomaly scores and need manually threshold setting, while existing LVLMs cannot detect anomalies in the image. AnomalyGPT can not only indicate the presence and location of anomaly but also provide information about the image.
+!()[./images/AnomalyGPT.png]
 We leverage a pre-trained image encoder and a Large Language Model (LLM) to align IAD images and their corresponding textual descriptions via simulated anomaly data. We employ a lightweight, visual-textual feature-matching-based image decoder to obtain localization result, and design a prompt learner to provide fine-grained semantic to LLM and fine-tune the LVLM using prompt embeddings. Our method can also detect anomalies for previously unseen items with few normal sample provided.
 ### License
+AnomalyGPT is licensed under the [CC BY-NC-SA 4.0 license](./LICENSE).
 ****