Distilling Generative-Discriminative Representations for Very Low-Resolution Face Recognition

TL;DR

This paper introduces a novel method combining generative and discriminative knowledge distillation to improve very low-resolution face recognition, effectively recovering facial details and enhancing recognition accuracy.

Contribution

It proposes a dual distillation framework using a diffusion model for generative features and a face recognizer for discriminative features, advancing low-resolution face recognition.

Findings

Improves recognition accuracy on low-resolution face datasets.

Effectively recovers facial details lost in low-resolution images.

Demonstrates superior performance over existing methods.

Abstract

Very low-resolution face recognition is challenging due to the serious loss of informative facial details in resolution degradation. In this paper, we propose a generative-discriminative representation distillation approach that combines generative representation with cross-resolution aligned knowledge distillation. This approach facilitates very low-resolution face recognition by jointly distilling generative and discriminative models via two distillation modules. Firstly, the generative representation distillation takes the encoder of a diffusion model pretrained for face super-resolution as the generative teacher to supervise the learning of the student backbone via feature regression, and then freezes the student backbone. After that, the discriminative representation distillation further considers a pretrained face recognizer as the discriminative teacher to supervise the learning of the student head via cross-resolution relational contrastive distillation. In this way, the general backbone representation can be transformed into discriminative head representation, leading to a robust and discriminative student model for very low-resolution face recognition. Our approach improves the recovery of the missing details in very low-resolution faces and achieves better knowledge transfer. Extensive experiments on face datasets demonstrate that our approach enhances the recognition accuracy of very low-resolution faces, showcasing its effectiveness and adaptability.