saberzl/SIDA-13B-description

SIDA Model Card

Model details

Model type:

SIDA-description is a model fine-tuned from SIDA, designed to explain the reason behind model decisions.

This description model is intended for explanation purposes only. If you want to validate experimental results, please use SIDA-13B instead.

Model date:

SIDA-13B-description was trained in Febuary 2025.

Paper or resources for more information:

Paper: https://arxiv.org/pdf/2412.04292

Resource: https://github.com/hzlsaber/SIDA

License

Llama 2 is licensed under the LLAMA 2 Community License, Copyright (c) Meta Platforms, Inc. All Rights Reserved.

Trained Data

SIDA was trained on SID_Set, which consists of real images, tampered images, and fully synthetic images. More information is available here

Citation Information

If you find this dataset useful, please consider citing our paper:

@misc{huang2025sidasocialmediaimage,
      title={SIDA: Social Media Image Deepfake Detection, Localization and Explanation with Large Multimodal Model}, 
      author={Zhenglin Huang and Jinwei Hu and Xiangtai Li and Yiwei He and Xingyu Zhao and Bei Peng and Baoyuan Wu and Xiaowei Huang and Guangliang Cheng},
      year={2025},
      booktitle={Conference on Computer Vision and Pattern Recognition}
}