Result Details
LossFIQA: A Shortcut Solution to Image Quality Assessment Using Loss for Faces and Beyond
We introduce a novel approach to model-based quality assessment of input images. Our approach is very simple, and we demonstrate experimentally that it is not limited to a single domain (typically face recognition in the literature). Our approach generates per-sample quality pseudo-labels directly from the objective function used during the training of the target model. We evaluate the proposed method on eight large and respected datasets (from the face recognition on LFW, CALFW, CPLFW, XQLFW, CFP-FP, AgeDB, IJB-C, and retinopathy detection domain on EyePACS dataset) and using multiple state-of-the-art models (AdaFace, MagFace, ArcFace, ElasticFace, and CuricularFace). Compared to state-of-the-art methods for face quality assessment that are considerably more complex, our solution yields competitive results while being much simpler and not limited to one application.
Biometry, computer vision, face recognition, face quality assessment, machine learning, quality assessment, semi-supervised learning
@article{BUT198680,
author="Marek {Vaško} and Adam {Herout}",
title="LossFIQA: A Shortcut Solution to Image Quality Assessment Using Loss for Faces and Beyond",
journal="IEEE Access",
year="2025",
volume="13",
number="7",
pages="126915--126924",
doi="10.1109/ACCESS.2025.3589778",
issn="2169-3536",
url="https://ieeexplore.ieee.org/document/11082134"
}