AI-KD: Towards Alignment Invariant Face Image Quality Assessment Using Knowledge Distillation

TL;DR

AI-KD is a novel knowledge distillation method that enhances face image quality assessment techniques, making them more robust to alignment variations and improving their performance across different face recognition scenarios.

Contribution

The paper introduces AI-KD, a knowledge distillation approach that extends existing FIQA methods to be alignment-invariant, addressing a key limitation in current face quality assessment techniques.

Findings

AI-KD improves FIQA performance on misaligned face samples.

AI-KD enhances robustness of FIQA across different alignment procedures.

AI-KD achieves state-of-the-art results when combined with existing FIQA methods.

Abstract

Face Image Quality Assessment (FIQA) techniques have seen steady improvements over recent years, but their performance still deteriorates if the input face samples are not properly aligned. This alignment sensitivity comes from the fact that most FIQA techniques are trained or designed using a specific face alignment procedure. If the alignment technique changes, the performance of most existing FIQA techniques quickly becomes suboptimal. To address this problem, we present in this paper a novel knowledge distillation approach, termed AI-KD that can extend on any existing FIQA technique, improving its robustness to alignment variations and, in turn, performance with different alignment procedures. To validate the proposed distillation approach, we conduct comprehensive experiments on 6 face datasets with 4 recent face recognition models and in comparison to 7 state-of-the-art FIQA techniques. Our results show that AI-KD consistently improves performance of the initial FIQA techniques not only with misaligned samples, but also with properly aligned facial images. Furthermore, it leads to a new state-of-the-art, when used with a competitive initial FIQA approach. The code for AI-KD is made publicly available from: https://github.com/LSIbabnikz/AI-KD.