Low-Resolution Face Recognition via Adaptable Instance-Relation Distillation

TL;DR

This paper introduces an adaptable instance-relation distillation method that improves low-resolution face recognition by enhancing knowledge transfer from high-resolution models and increasing adaptability during inference.

Contribution

It proposes a novel two-step knowledge transfer and adaptation framework that significantly improves low-resolution face recognition performance.

Findings

Effective cross-resolution knowledge transfer demonstrated

Enhanced adaptability with adaptive batch normalization

Superior performance on low-resolution face recognition benchmarks

Abstract

Low-resolution face recognition is a challenging task due to the missing of informative details. Recent approaches based on knowledge distillation have proven that high-resolution clues can well guide low-resolution face recognition via proper knowledge transfer. However, due to the distribution difference between training and testing faces, the learned models often suffer from poor adaptability. To address that, we split the knowledge transfer process into distillation and adaptation steps, and propose an adaptable instance-relation distillation approach to facilitate low-resolution face recognition. In the approach, the student distills knowledge from high-resolution teacher in both instance level and relation level, providing sufficient cross-resolution knowledge transfer. Then, the learned student can be adaptable to recognize low-resolution faces with adaptive batch normalization in inference. In this manner, the capability of recovering missing details of familiar low-resolution faces can be effectively enhanced, leading to a better knowledge transfer. Extensive experiments on low-resolution face recognition clearly demonstrate the effectiveness and adaptability of our approach.