Giter VIP home page Giter VIP logo

genimage's Introduction

GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image [Homepage]

Mingjian Zhu, Hanting Chen, Qiangyu Yan, Xudong Huang, Guanyu Lin, Wei Li, Zhijun Tu, Hailin Hu, Jie Hu, Yunhe Wang

This is a temporary repository. The content has moved to our official repository.

We strongly recommend you visit our official repository.

We also recommend you visit our homepage.

If this project helps you, please fork, watch, and give a star to our official repository.

Official Repository: https://github.com/GenImage-Dataset/GenImage

Homepage: https://genimage-dataset.github.io/

Reference

If you find our repository useful for your research, please consider citing our paper:

@misc{zhu2023genimage,
      title={GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image}, 
      author={Mingjian Zhu and Hanting Chen and Qiangyu Yan and Xudong Huang and Guanyu Lin and Wei Li and Zhijun Tu and Hailin Hu and Jie Hu and Yunhe Wang},
      year={2023},
      eprint={2306.08571},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

genimage's People

Contributors

andrew-zhu avatar

Stargazers

Haoming Lu avatar Brook Ji avatar MedicineStick avatar avatar Yang FanChiang avatar mimi avatar avatar Zheling Meng avatar avatar lyricpoem avatar Qing Chen avatar avatar tuzhijun avatar avatar avatar avatar avatar yongzhang6782 avatar Linyz avatar Yuchong Yao avatar EX MACHINE GOD avatar Chaofeng Chen avatar HelenFuzhou avatar avatar

Watchers

avatar

Forkers

genimage-dataset

genimage's Issues

Issue with dataset uploaded on Google Drive

Hi.

Thank you for granting access to this wonderful dataset.

I have been examining the data and noticed a potential inconsistency that I wanted to bring to your attention. It appears that the multi-part zip files located in the “ADM” folder on Google Drive are showing as zero bytes in size.

If it’s not too much trouble, could you please look into this matter and possibly re-upload the corresponding files? I apologize for any inconvenience this may cause.

Thank You and Regards

Class information

Thanks for your great work! Is it possible to get information about the class for every image? Maybe a meta-csv? As you mentioned in your paper, separating classes for training/testing is an important problem

About model architectures

Hi, your work is great and fascinating, but I have some questions about the models mentioned in the paper. How do you adjust the model to fit the task and how much data did you use for training these models. And I would be appreciated if the weights of the model could be provided.

baidu netdisk code

An influential work.

Could you provide the code of baidu netdisk to download the dataset?

Corrupted Files

Thanks for your great work! But when i download it from baidu (which is by the way very difficult for europeans), there are in total 17 corrupted files/images

Inquiry about weights

Excellent work! I believe it deserves acceptance. Do you have any plan to share the weights of the chosen models trained on the different protocols you set (especially in Tables 2,3, and 4)?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.