Abstract
Low-resolution face recognition (LRFR) has become a challenging problem for modern deep face recognition systems. Existing methods mainly leverage prior information from high-resolution (HR) images by either reconstructing facial details with super-resolution techniques or learning a unified feature space. To address this issue, this paper proposes a novel approach which enforces the network to focus on the discriminative information stored in the low-frequency components of a low-resolution (LR) image. A cross-resolution knowledge distillation paradigm is first employed as the learning framework. An identity-preserving network, WaveResNet, and a wavelet similarity loss are then designed to capture low-frequency details and boost performance. Finally, an image degradation model is conceived to simulate more realistic LR training data. Consequently, extensive experimental results show that the proposed method consistently outperforms the baseline model and other state-of-the-art methods across a variety of image resolutions.
Abstract (translated)
低分辨率人脸识别(LRFR)已成为现代深度人脸识别系统的挑战性问题。现有的方法主要利用高分辨率(HR)图像的先前信息,通过使用超分辨率技术或学习一个统一的特征空间来重建面部细节。为了解决这个问题,本文提出了一种新 approach,该方法强迫网络关注低分辨率(LR)图像中存储的区分信息,即低频率成分。一种跨分辨率知识蒸馏范式被用作学习框架。一个保持身份的网络、 WaveResNet 和小波相似度损失被设计用于捕获低频率细节并提高性能。最后,一个图像退化模型被构思以模拟更真实的LR训练数据。因此,广泛的实验结果显示,所提出的方法在不同图像分辨率下 consistently outperforms 基准模型和其他现代方法。
URL
https://arxiv.org/abs/2303.08665
