Data scarcity and distribution shift pose major challenges for masked face detection and recognition. We propose a two-step generative data augmentation framework that combines rule-based mask warping with unpaired image-to-image translation using GANs, enabling the generation of realistic masked-face samples beyond purely synthetic transformations. Compared to rule-based warping alone, the proposed approach yields consistent qualitative improvements and complements existing GAN-based masked face generation methods such as IAMGAN. We introduce a non-mask preservation loss and stochastic noise injection to stabilize training and enhance sample diversity. Experimental observations highlight the effectiveness of the proposed components and suggest directions for future improvements in data-centric augmentation for face recognition tasks.

翻译：数据稀缺与分布偏移是遮挡人脸检测与识别面临的主要挑战。本文提出一种两步式生成数据增强框架，该框架结合基于规则的口罩形变与使用生成对抗网络（GAN）的非配对图像到图像转换技术，能够生成超越纯合成变换的真实感遮挡人脸样本。与单独使用基于规则的形变方法相比，所提方法在定性上取得了一致的改进，并对现有基于GAN的遮挡人脸生成方法（如IAMGAN）形成了补充。我们引入了非口罩区域保持损失与随机噪声注入机制，以稳定训练过程并提升样本多样性。实验结果凸显了所提组件的有效性，并为以数据为中心的人脸识别任务增强方法指明了未来改进方向。