# Zooming into Face Forensics: A Pixel-level Analysis

arXiv: https://arxiv.org/abs/1912.05790 · HTML: https://mlsanity.com/paper/1912.05790/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2019.

## Built on by (most cited first, 6 of 6)

- [Face Forensics in the Wild](https://mlsanity.com/paper/2103.16076/) (2021)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection](https://mlsanity.com/paper/2212.05667/) (2022)
- [Collaborative Feature Learning for Fine-grained Facial Forgery Detection and Segmentation](https://mlsanity.com/paper/2304.08078/) (2023)
- [DF-Captcha: A Deepfake Captcha for Preventing Fake Calls](https://mlsanity.com/paper/2208.08524/) (2022)
- [Deepfake Caricatures: Amplifying attention to artifacts increases deepfake detection by humans and machines](https://mlsanity.com/paper/2206.00535/) (2022)

## Abstract (arXiv)

The stunning progress in face manipulation methods has made it possible to synthesize realistic fake face images, which poses potential threats to our society. It is urgent to have face forensics techniques to distinguish those tampered images. A large scale dataset "FaceForensics++" has provided enormous training data generated from prominent face manipulation methods to facilitate anti-fake research. However, previous works focus more on casting it as a classification problem by only considering a global prediction. Through investigation to the problem, we find that training a classification network often fails to capture high quality features, which might lead to sub-optimal solutions. In this paper, we zoom in on the problem by conducting a pixel-level analysis, i.e. formulating it as a pixel-level segmentation task. By evaluating multiple architectures on both segmentation and classification tasks, We show the superiority of viewing the problem from a segmentation perspective. Different ablation studies are also performed to investigate what makes an effective and efficient anti-fake model. Strong baselines are also established, which, we hope, could shed some light on the field of face forensics.