# Two-Step Data Augmentation for Masked Face Detection and Recognition: Turning Fake Masks to Real

arXiv: https://arxiv.org/abs/2512.15774 · HTML: https://mlsanity.com/paper/2512.15774/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 13 Dec 2025.

## Builds on (most cited first, 15 of 15)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Deep Face Recognition: A Survey](https://mlsanity.com/paper/1804.06655/) (2018)
- [GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium](https://mlsanity.com/paper/1706.08500/) (2017)
- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [One-Sided Unsupervised Domain Mapping](https://mlsanity.com/paper/1706.00826/) (2017)
- [AttentionGAN: Unpaired Image-to-Image Translation using Attention-Guided Generative Adversarial Networks](https://mlsanity.com/paper/1911.11897/) (2019)
- [Cross-View Image Synthesis using Conditional GANs](https://mlsanity.com/paper/1803.03396/) (2018)
- [Masked Face Recognition Dataset and Application](https://mlsanity.com/paper/2003.09093/) (2020)
- [Masked Face Recognition for Secure Authentication](https://mlsanity.com/paper/2008.11104/) (2020)
- [MaskedFace-Net -- A Dataset of Correctly/Incorrectly Masked Face Images in the Context of COVID-19](https://mlsanity.com/paper/2008.08016/) (2020)
- [A Survey on Face Data Augmentation](https://mlsanity.com/paper/1904.11685/) (2019)
- [Boosting Masked Face Recognition with Multi-Task ArcFace](https://mlsanity.com/paper/2104.09874/) (2021)
- [MLFW: A Database for Face Recognition on Masked Faces](https://mlsanity.com/paper/2109.05804/) (2021)

## Abstract (arXiv)

The absence of large-scale masked face datasets challenges masked face detection and recognition. We propose a two-step generative data augmentation framework combining rule-based mask warping with unpaired image-to-image translation via GANs, producing masked face samples that go beyond rule-based overlays. Trained on about 19,100 images in the target domain (3.8% of IAMGAN's scale), or, including out-of-domain transfer pretraining, 59,600 and 11.8%, the proposed approach yields consistent improvements over rule-based warping alone and achieves results complementary to IAMGAN's, showing that both steps contribute. Evaluation is conducted directly on the generated samples and is qualitative; quantitative metrics like FID and KID were not applied as any real reference distribution would unfairly favor the model with closer training data. We introduce a non-mask preservation loss to reduce non-mask distortions and stabilize training, and stochastic noise injection to enhance sample diversity. Note: The paper originated as a coursework project completed under resource constraints. Following scholarship termination, the author took on part-time employment to maintain research continuity, which led to a mid-semester domain pivot from medical imaging to masked face tasks due to company data restrictions. The work was completed alongside concurrent coursework with delayed compute access and without AI assistance. It was submitted at the semester end to meet a publication requirement, accepted without revision requests, and selected among the best papers for an extended submission to Springer Nature Computer Science, which was not pursued due to continued funding absence. Downstream evaluation on recognition or detection performance was not completed by the submission deadline. The note is added in response to subsequent comparisons and criticisms that did not account for these conditions.