This is an ONNX version of buildborderless/CommunityForensics-DeepfakeDet-ViT. It was automatically converted and uploaded using this Hugging Face Space.
See the pipeline documentation for image-classification: https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.ImageClassificationPipeline
Model presented in Community Forensics: Using Thousands of Generators to Train Fake Image Detectors.
Uploaded for community validation as part of OpenSight - An upcoming open-source framework for adaptive deepfake detection.
Project OpenSight HF Spaces coming soon with an eval playground and eventually a leaderboard. Preview:
Vision Transformer (ViT) model trained on the largest dataset to-date for detecting AI-generated images in forensic applications.
HF Space will be open sourced shortly showcasing various ways to run ultra-fast inference. Make sure to follow us for updates, as we will be releasing a slew of projects in the coming weeks.
| Metric | Value |
|---|---|
| Accuracy | 97.2% |
| F1 Score | 0.968 |
| AUC-ROC | 0.992 |
| FP Rate | 2.1% |
BibTeX:
@misc{park2024communityforensics,
title={Community Forensics: Using Thousands of Generators to Train Fake Image Detectors},
author={Jeongsoo Park and Andrew Owens},
year={2024},
eprint={2411.04125},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2411.04125},
}
onnx/model.onnx 144 MBonnx/model_fp16.onnx 72 MBonnx/model_uint8.onnx 37 MBonnx/model_int8.onnx 37 MBonnx/model_quantized.onnx 37 MBonnx/model_bnb4.onnx 24 MBonnx/model_q4.onnx 24 MBonnx/model_q4f16.onnx 21 MBbuildborderless/CommunityForensics-DeepfakeDet-ViT