Face Image Quality Vector Assessment for Biometrics Applications

Najafzadeh, Nima; Kashiani, Hossein; Ebrahimi, Saadabadi, Mohammad Saeed; Alipour, Talemi, Niloufar; Malakshan, Sahar Rahimi; Nasrabadi, Nasser M.

doi:10.1109/wacvw58289.2023.00057

Cited by 8 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sometimes, the face in image could be detected, but could not be reliably recognized. To filter such images, and to measure the quality and the recognizability of faces, one could use face quality estimation methods [21] such as CR-FIQA [37], FaceQAN [38], L2RT-FIQA [39], DifFIQA [40] and others [27], [41]- [48]. Sometimes these methods are inserted in the process of face representation learning [19], [23], [49]- [55], improving the results with more precise training signals.…”

Section: B Face Quality Estimationmentioning

confidence: 99%

Prototype Memory for Large-Scale Face Representation Learning

Smirnov¹,

Garaev²,

Galyuk³

2022

IEEE Access

View full text Add to dashboard Cite

Face representation learning using datasets with a massive number of identities requires appropriate training methods. Softmax-based approach, currently the state-of-the-art in face recognition, in its usual "full softmax" form is not suitable for datasets with millions of persons. Several methods, based on the "sampled softmax" approach, were proposed to remove this limitation. These methods, however, have a set of disadvantages. One of them is a problem of "prototype obsolescence": classifier weights (prototypes) of the rarely sampled classes, receive too scarce gradients and become outdated and detached from the current encoder state, resulting in incorrect training signals. This problem is especially serious in ultra-large-scale datasets. In this paper, we propose a novel face representation learning model called Prototype Memory, which alleviates this problem and allows training on a dataset of any size. Prototype Memory consists of the limited-size memory module for storing recent class prototypes and employs a set of algorithms to update it in appropriate way. New class prototypes are generated on the fly using exemplar embeddings in the current mini-batch. These prototypes are enqueued to the memory and used in a role of classifier weights for softmax classification-based training. To prevent obsolescence and keep the memory in close connection with the encoder, prototypes are regularly refreshed, and oldest ones are dequeued and disposed of. Prototype Memory is computationally efficient and independent of dataset size. It can be used with various loss functions, hard example mining algorithms and encoder architectures. We prove the effectiveness of the proposed model by extensive experiments on popular face recognition benchmarks.

show abstract

Section: B Face Quality Estimationmentioning

confidence: 99%

Prototype Memory for Large-Scale Face Representation Learning

Smirnov¹,

Garaev²,

Galyuk³

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…1 [14]. Generally, face image quality reflects the understandable nuisance factors in the face image such as pose-angle, illumination, distortion, and resolution [15], [16]. However, task-related image quality is the key to boosting the deep model performance [17].…”

Section: Introductionmentioning

confidence: 99%

Joint Super-Resolution and Head Pose Estimation for Extreme Low-Resolution Faces

et al. 2023

Self Cite

View full text Add to dashboard Cite

State-of-the-art deep learning-based Head Pose Estimation (HPE) techniques have reached spectacular performance on High-Resolution (HR) face images. However, they still fail to achieve expected performance on low-resolution images at large scales. This work presents an end-to-end HPE framework assisted by a Face Super-Resolution (FSR) algorithm. The proposed FSR model is specifically guided to enhance the HPE performance rather than considering FSR as an independent task. To this end, we utilized a Multi-Stage Generative Adversarial Network (MSGAN) which benefit from a pose-aware adversarial loss and head pose estimation feedback to generate super-resolved images that are properly aligned for HPE. Also, we propose a degradation strategy rather than simple down-sampling approach to mimic the diverse properties of real-world Low-Resolution (LR) images. We evaluate the performance of our proposed method on both synthetic and real-world LR datasets and show the superiority of our approach in both visual and HPE metrics on the AFLW2000, BIWI, and WiderFace Datasets.INDEX TERMS Head pose estimation (HPE), face super-resolution (FSR), multi-stage generative adversarial networks (MSGAN), low-resolution (LR) face images.

show abstract

Diffusion-based normality pre-training for weakly supervised video anomaly detection

Basak,

Gautam

2024

Expert Systems with Applications

View full text Add to dashboard Cite

Face Image Quality Vector Assessment for Biometrics Applications

Cited by 8 publications

References 31 publications

Prototype Memory for Large-Scale Face Representation Learning

Prototype Memory for Large-Scale Face Representation Learning

Joint Super-Resolution and Head Pose Estimation for Extreme Low-Resolution Faces

Diffusion-based normality pre-training for weakly supervised video anomaly detection

Contact Info

Product

Resources

About