Real-time masked face classification and head pose estimation for RGB facial image via knowledge distillation

Thai, Chien; Tran, Viet; Bui, Minh; Nguyen, Dat Tien; Ninh, Huong; Tien, Hai Tran

doi:10.1016/j.ins.2022.10.074

Cited by 9 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Face recognition systems have been widely used in a variety of applications, including visual surveillance (Zhang et al, 2018), automated border control (del Rio et al, 2016), education systems (Jadhav et al, 2021) and healthcare (Bargshady et al, 2020). Face recognition technology needs to be more efficient while confronting obstacles such as varying illumination (Koley et al, 2022), low resolution (Zangeneh et al, 2020), different pose (Thai et al, 2022), expression change (Huang et al, 2021) and occlusion (Long et al, 2018; Peng et al, 2023; Zeng et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

ABANet: Attention boundary‐aware network for image segmentation

Rezvani,

Fateh,

Khosravi

2024

Expert Systems

View full text Add to dashboard Cite

Deep learning techniques have attained substantial progress in various face‐related tasks, such as face recognition, face inpainting, and facial expression recognition. To prevent infection or the spread of the virus, wearing of masks in public places has been mandated following the COVID‐19 epidemic, which has led to face occlusion and posed significant challenges for face recognition systems. Most prominent masked face recognition solutions rely on mask segmentation tasks. Therefore, segmentation can be used to mitigate the negative impacts of wearing a mask and improve recognition accuracy. Mask region segmentation suffers from two main problems: there is no standard type of masks that people wear, they come in different colours and designs, and there is no publicly available masked face dataset with appropriate ground truth for the mask region. In order to address these issues, we propose an encoder–decoder framework that utilizes a boundary‐aware attention network combined with a new hybrid loss to provide a map, patch, and pixel‐level supervision. We also introduce a dataset called MFSD, with 11,601 images and 12,758 masked faces for masked face segmentation. Furthermore, we compare the performance of different cutting‐edge deep learning semantic segmentation models on the presented dataset. Experimental results on the MSFD dataset reveal that the suggested approach outperforms state‐of‐the‐art, algorithms with 97.623% accuracy, 93.814% IoU, and 96.817% F1‐score rate. Our dataset of masked faces with mask region labels and source code will be available online.

show abstract

Section: Introductionmentioning

confidence: 99%

ABANet: Attention boundary‐aware network for image segmentation

Rezvani,

Fateh,

Khosravi

2024

Expert Systems

View full text Add to dashboard Cite

show abstract

“…Unlike several other methods that require a tailor-made solution for every different network structure and even dataset, KD can be applied to different network structures and datasets only by designing a unified framework, which has wider practical applications. [18][19][20] KD was originally proposed by Hinton et al 12 The core idea is to exploit the knowledge of a heavy but powerful teacher network to help train a small and lightweight student network and improve the performance of the student network as much as possible. Kullback-Leibler (KL) divergence is a measure used to quantify the difference between two probability distributions.…”

Section: Introductionmentioning

confidence: 99%

“… – 17 Among these methods, KD provides a simple, effective, and universal solution. Unlike several other methods that require a tailor-made solution for every different network structure and even dataset, KD can be applied to different network structures and datasets only by designing a unified framework, which has wider practical applications 18 – 20 …”

Section: Introductionmentioning

confidence: 99%

Cross-stage distillation with inverted bottleneck projectors

Sun,

Liu,

Zhang

et al. 2023

J. Electron. Imag.

View full text Add to dashboard Cite

Knowledge distillation, which transfers knowledge from a large model (the teacher) to a small model (the student), is a promising way in the field of lightweight model design. Existing distillation methods based on intermediate features mainly focus on knowledge transfer between the same stages of teacher and student networks, which may lead to student networks receiving semantically mismatched knowledge and missing contextual knowledge. To solve this problem, a cross-stage distillation with inverted bottleneck projectors is proposed. A cross-stage connection structure is designed that enables the student network to access the teacher network's most matched stages in semantics and further obtain rich contextual knowledge from multiple stages of the teacher. After establishing the cross-stage connection between the teacher network and the student network, inverted bottleneck projectors are employed to extract useful knowledge from multiple stages of the teacher. A stack structure with three-layer convolutions is proposed in every projector, which can make the knowledge of the teacher network more easily understood by the student network. The inverted bottleneck structure can reduce information loss, ensuring the integrity of knowledge transmission. Further, ReLU activations are incorporated into the projectors to remove features with lower response values, thereby filtering redundant elements. Extensive experiments on CIFAR100, ImageNet, Tiny-ImageNet, and STL-10 datasets demonstrate the effectiveness of the proposed approach.

show abstract