Lipface: Lipschitz-Conditioned For Resolution Robust Face Recognition

Face recognition (FR) has achieved unprecedented success in high-resolution face recognition (HRFR) scenarios. However, applying the models trained on HRFR tasks to cross-resolution face recognition (CRFR) or low-resolution face recognition (LRFR) results in performance decline. This is attributed to the challenges in extracting identity-preserving features from low-resolution images. To address this, we present Lipface, an FR model fortified with Lipschitz constraints, designed to perform robustly across varying face resolutions. Also, recognizing the differential impact of training images based on their quality, we adopt the feature norm as an image quality metric. This allows our model to weigh the significance of samples during training dynamically. Experiments demonstrate that, under various backbones and training datasets, Lipface outperforms state-of-the-art FR methods. Across two HRFR datasets (LFW and IJBB), one LRFR dataset (Tinyface), and two CRFR datasets (SCface and XQLFW), Lipface achieves an average improvement ranging from 1.92% to 6.07% across the five datasets.