In this paper, we tackle the challenge of face recognition in the wild, where images often suffer from low quality and real-world distortions. Traditional heuristic approaches-either training models directly on these degraded images or their enhanced counterparts using face restoration techniques-have proven ineffective, primarily due to the degradation of facial features and the discrepancy in image domains. To overcome these issues, we propose an effective adapter for augmenting existing face recognition models trained on high-quality facial datasets. The key of our adapter is to process both the unrefined and the enhanced images by two similar structures where one is fixed and the other trainable. Such design can confer two benefits. First, the dual-input system minimizes the domain gap while providing varied perspectives for the face recognition model, where the enhanced image can be regarded as a complex non-linear transformation of the original one by the restoration model. Second, both two similar structures can be initialized by the pre-trained models without dropping the past knowledge. The extensive experiments in zero-shot settings show the effectiveness of our method by surpassing baselines of about 3%, 4%, and 7% in three datasets. Our code will be publicly available at https://github.com/liuyunhaozz/FaceAdapter/.

翻译：本文针对野外场景中的人脸识别挑战展开研究，此类场景下的图像常受低质量与真实世界畸变影响。传统的启发式方法——无论是直接在退化图像上训练模型，还是采用人脸修复技术处理增强版本——均被证明效果有限，主要原因在于面部特征退化以及图像域差异。为解决上述问题，我们提出一种高效适配器，用于增强现有基于高质量人脸数据集训练的人脸识别模型。该适配器的核心在于通过两个结构相似的模块处理原始未优化图像与增强图像：其中一个模块保持固定参数，另一个模块可训练。这种设计具有双重优势：首先，双输入系统可在为人脸识别模型提供多样化视角的同时最小化域差异，其中增强图像可视为经过修复模型对原始图像实施的复杂非线性变换；其次，两个相似结构均可通过预训练模型初始化，从而保留历史知识。在零样本设置下的大规模实验表明，本方法在三个数据集上分别超越基线约3%、4%和7%。相关代码将开源至https://github.com/liuyunhaozz/FaceAdapter/。