Developed by: Jeongsoo Park and Andrew Owens, University of Michigan
Model type: Vision Transformer (ViT-Small)
License: MIT (compatible with CreativeML OpenRAIL-M referenced in [2411.04125v1.pdf])
Finetuned from: timm/vit_small_patch16_384.augreg_in21k_ft_in1k
Adapted for HF inference compatibility by AI Without Borders.

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.

Training Details

Training Data

2.7mil images from 15+ generators, 4600+ models
Over 1.15TB worth of images

Training Hyperparameters

Framework: PyTorch 2.0
Precision: bf16 mixed
Optimizer: AdamW (lr=5e-5)
Epochs: 10
Batch Size: 32

Evaluation

Unverified Testing Results

Only unverified because we currently lack resources to evaluate a dataset over 1.4T large.

Metric	Value
Accuracy	97.2%
F1 Score	0.968
AUC-ROC	0.992
FP Rate	2.1%

Re-sampled and refined dataset

Coming soon™

Citation

BibTeX:

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-community/CommunityForensics-DeepfakeDet-ViT-ONNX

CommunityForensics-DeepfakeDet-ViT (ONNX)

Usage with Transformers.js

Trained on 2.7M samples across 4,803 generators (see Training Data)

Model Details

Model Description

Links