A deep transfer learning approach to fine-tuning facial recognition models

Luttrell, Joseph; Zhou, Zhaoxian; Zhang, Yuanyuan; Zhang, Chaoyang; Gong, Ping; Yang, Beifang; Li, Runzhi

doi:10.1109/iciea.2018.8398162

Cited by 17 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accuracy J. Luttrel et al [27] 85.7 Hariri et al [28] 84.6 Almabdy et al [10] 87.0 Walid Hariri. [15] 91. spatial information in the inference stage.…”

Section: Methodsmentioning

confidence: 99%

Masked Face Recognition With Mask Transfer and Self-Attention Under the COVID-19 Pandemic

et al. 2022

View full text Add to dashboard Cite

Face masks bring a new challenge to face recognition systems especially against the background of the COVID-19 pandemic. In this paper, a method mitigating the negative effects of mask defects on face recognition is proposed. Firstly, a low-cost, accurate method of masked face synthesis, i.e. mask transfer, is proposed for data augmentation. Secondly, an attention-aware masked face recognition (AMaskNet) is proposed to improve the performance of masked face recognition, which includes two modules: a feature extractor and a contribution estimator. Therein, the contribution estimator is employed to learn the contribution of the feature elements, thus achieving refined feature representation by simple matrix multiplications. Meanwhile, the end-to-end training strategy is utilized to optimize the entire model. Finally, a mask-aware similarity matching strategy(MS) is taken to improve the performance in the inference stage. The experiments show that the proposed method consistently outperforms on three masked face recognition datasets: RMFRD [1], COX [2] and Public-IvS [3]. Meanwhile, qualitative analysis experiments using CAM [4] indicate that the contribution learned by AMaskNet is more conducive to masked face recognition. INDEX TERMS Masked face recognition, mask transfer, face synthesis, attention mechanism.

show abstract

“…Accuracy J. Luttrel et al [27] 85.7 Hariri et al [28] 84.6 Almabdy et al [10] 87.0 Walid Hariri. [15] 91. spatial information in the inference stage.…”

Section: Methodsmentioning

confidence: 99%

Masked Face Recognition With Mask Transfer and Self-Attention Under the COVID-19 Pandemic

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In the YCBCR color space, the non-occluded face spectrogram was able to retain more high-frequency detail information. Therefore, it the YCBCR color space may be considered more suitable for feature extraction from non-occluded faces [40].…”

Section: ) Influence Of Different Color Spaces On Fbbmentioning

confidence: 99%

Face Recognition With Masks Based on Spatial Fine-Grained Frequency Domain Broadening

Chen

Xie

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Along with social distancing, wearing masks is an effective method of preventing the transmission of COVID-19 in the ongoing pandemic. However, masks occlude a large number of facial features, preventing facial recognition. The recognition rate of existing methods may be significantly reduced by the presence of masks. In this paper, we propose a method to effectively solve the problem of the lack of facial feature information needed to perform facial recognition on people wearing masks. The proposed approach uses image super-resolution technology to perform image preprocessing along with a deep bilinear module to improve EfficientNet. It also combines feature enhancement with frequency domain broadening, fuses the spatial features and frequency domain features of the unoccluded areas of the face, and classifies the fused features. The features of the unoccluded area are increased to improve the accuracy of recognition of masked faces. The results of a cross-validation show that the proposed approach achieved an accuracy of 98% on the RMFRD dataset, as well as a higher recognition rate and faster speed than previous methods. In addition, we also performed an experimental evaluation in an actual facial recognition system and achieved an accuracy of 99%, which demonstrates the effectiveness and practicability of the proposed method.INDEX TERMS Face recognition with mask, convolutional neural network, frequency domain widening, bilinear module, RMFRD dataset.

show abstract

“…To avoid this, transfer learning approach is gaining popularity among researchers which saves a lot of time and resources by the use of pre-trained networks for feature extraction. In this approach the learned weights from the pre-trained network layers are used for feature extraction [38, 39, 12, 40, 41]. The above discussion shows that the conventional machine learning methods such as, sparse based representation method performs well with even with limited data but only on constrained data whereas the deep learning models perform fantastically well even on unconstrained data but the method requires large amount of training data.…”

Section: Literature Surveymentioning

confidence: 99%

Real Time Face Recognition with limited training data: Feature Transfer Learning integrating CNN and Sparse Approximation

Bajpai

Mishra

2021

Preprint

View full text Add to dashboard Cite

It is highly challenging to obtain high performance with limited and unconstrained data in real time face recognition applications. Sparse Approximation is a fast and computationally efficient method for the above application as it requires no training time as compared to deep learning methods. It eliminates the training time by assuming that the test image can be approximated by the sum of individual contributions of the training images from different classes and the class with maximum contribution is closest to the test image. The efficiency of the Sparse Approximation method can be further increased by providing high quality features as input for classification. Hence, we propose to integrate pre-trained CNN architecture to extract the highly discriminative features from the image dataset for Sparse classification. The proposed approach provides better performance even for one training image per class in complex environment as compared to the existing methods. Highlight of the present approach is the results obtained for LFW dataset with one and thirteen training images per class are 84.86% and 96.14% respectively, whereas the existing deep learning methods use a large amount of training data to achieve comparable results.

show abstract

A deep transfer learning approach to fine-tuning facial recognition models

Cited by 17 publications

References 12 publications

Masked Face Recognition With Mask Transfer and Self-Attention Under the COVID-19 Pandemic

Masked Face Recognition With Mask Transfer and Self-Attention Under the COVID-19 Pandemic

Face Recognition With Masks Based on Spatial Fine-Grained Frequency Domain Broadening

Real Time Face Recognition with limited training data: Feature Transfer Learning integrating CNN and Sparse Approximation

Contact Info

Product

Resources

About