DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
Authors:
Top Cited Papers
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2886-2895
Abstract
We present our on-going effort of constructing a large- scale benchmark for face forgery detection. The first version of this benchmark, DeeperForensics-1.0, represents the largest face forgery detection dataset by far, with 60, 000 videos constituted by a total of 17.6 million frames, 10 times larger than existing datasets of the same kind. Extensive real-world perturbations are applied to obtain a more challenging benchmark of larger scale and higher diversity. All source videos in DeeperForensics-1.0 are carefully collected, and fake videos are generated by a newly proposed end-to-end face swapping framework. The quality of generated videos outperforms those in existing datasets, validated by user studies. The benchmark features a hidden test set, which contains manipulated videos achieving high deceptive scores in human evaluations. We further contribute a comprehensive study that evaluates five representative detection baselines and make a thorough analysis of different settings.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Two-Stream Neural Networks for Tampered Face Detection2017
- Recasting Residual-based Local Descriptors as Convolutional Neural Networks2017
- Demo of Face2Face2016
- A Deep Learning Approach to Universal Image Manipulation Detection Using a New Convolutional Layer2016
- Deep Residual Learning for Image Recognition2016
- Learning Spatiotemporal Features with 3D Convolutional Networks2015
- Detecting image splicing in the wild (WEB)2015
- Image database TID2013: Peculiarities, results and perspectivesSignal Processing: Image Communication, 2015
- Rich Models for Steganalysis of Digital ImagesIEEE Transactions on Information Forensics and Security, 2012
- Long Short-Term MemoryNeural Computation, 1997