MagFace: A Universal Representation for Face Recognition and Quality Assessment

Meng, Qiang; Zhao, Shichao; Huang, Zhida; Zhou, Feng

doi:10.48550/arxiv.2103.06627

Cited by 12 publications

(17 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The only surveyed approaches that fall into this category are the recent monolithic łdata uncertainty learningž [49] and łMagFacež [44]. Most recently, the latter has also been included in pure evaluation literature [41][40].…”

Section: Aspect: Datamentioning

confidence: 99%

See 1 more Smart Citation

Face Image Quality Assessment: A Literature Survey

et al. 2022

View full text Add to dashboard Cite

The performance of face analysis and recognition systems depends on the quality of the acquired face data, which is influenced by numerous factors. Automatically assessing the quality of face data in terms of biometric utility can thus be useful to detect low-quality data and make decisions accordingly. This survey provides an overview of the face image quality assessment literature, which predominantly focuses on visible wavelength face image input. A trend towards deep learning based methods is observed, including notable conceptual differences among the recent approaches, such as the integration of quality assessment into face recognition models. Besides image selection, face image quality assessment can also be used in a variety of other application scenarios, which are discussed herein. Open issues and challenges are pointed out, i.a. highlighting the importance of comparability for algorithm evaluations, and the challenge for future work to create deep learning approaches that are interpretable in addition to providing accurate utility predictions.

show abstract

Section: Aspect: Datamentioning

confidence: 99%

“…CNN IQA [170] on various facial areas (eyes, nose, mouth, averaged fusion) and on cropped or aligned images. Compared against monolithic FIQAAs [60][53][50] [44].…”

Section: Monolithic -Literature Introductionsmentioning

confidence: 99%

Face Image Quality Assessment: A Literature Survey

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To enable this behavior, most existing FR systems adopt the training methodology proposed by [65] in 2015: adding an extra loss function during model training to directly optimize for large separations between different faces in the feature space. Followup works explore alternative loss functions and model architectures to further improve the accuracy of FR systems (e.g., [63], [64], [66]).…”

Section: Image Preprocessingmentioning

confidence: 99%

SoK: Anti-Facial Recognition Technology

Wenger¹,

Shan²,

Zheng³

et al. 2021

Preprint

View full text Add to dashboard Cite

The rapid adoption of facial recognition (FR) technology by both government and commercial entities in recent years has raised concerns about civil liberties and privacy. In response, a broad suite of so-called "anti-facial recognition" (AFR) tools has been developed to help users avoid unwanted facial recognition. The set of AFR tools proposed in the last few years is wide-ranging and rapidly evolving, necessitating a step back to consider the broader design space of AFR systems and long-term challenges. This paper aims to fill that gap and provides the first comprehensive analysis of the AFR research landscape. Using the operational stages of FR systems as a starting point, we create a systematic framework for analyzing the benefits and tradeoffs of different AFR approaches. We then consider both technical and social challenges facing AFR tools and propose directions for future research in this field.

show abstract

“…Inspired by [23], the authors propose an adaptive mechanism based on the magnitude which can measure the quality of the given sample. This prevents models from overfitting on noisy low-quality samples.…”

Section: Chunk-based Marginmentioning

confidence: 99%

Adaptive Margin Circle Loss for Speaker Verification

Xiao¹

2021

Preprint

View full text Add to dashboard Cite

Deep-Neural-Network (DNN) based speaker verification systems use the angular softmax loss with margin penalties to enhance the intra-class compactness of speaker embeddings, which achieved remarkable performance. In this paper, we propose a novel angular loss function called adaptive margin circle loss for speaker verification. The stage-based margin and chunk-based margin are applied to improve the angular discrimination of circle loss on the training set. The analysis on gradients shows that, compared with the previous angular loss like Additive Margin Softmax(Am-Softmax), circle loss has flexible optimization and definite convergence status. Experiments are carried out on the Voxceleb and SITW. By applying adaptive margin circle loss, our best system achieves 1.31%EER on Voxceleb1 and 2.13% on SITW core-core.

show abstract

MagFace: A Universal Representation for Face Recognition and Quality Assessment

Cited by 12 publications

References 47 publications

Face Image Quality Assessment: A Literature Survey

Face Image Quality Assessment: A Literature Survey

SoK: Anti-Facial Recognition Technology

Adaptive Margin Circle Loss for Speaker Verification

Contact Info

Product

Resources

About