(Retracted) Estimation of human age by features of face and eyes based on multilevel feature convolutional neural network

Yi, Tangtang

doi:10.1117/1.jei.31.4.041208

Cited by 3 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In MBConv module, depth separable convolution [16] is used to replace the standard convolution of the original 3×3, and the comparison of its calculation amount and parameter amount are shown in formula ( 1) and (2). (4) where in C represents the input channel of the module, out C represents the output channel of the module, T represents the magnification factor of convolution dimension, T andW represent the height and width of the characteristic graph respectively, and the amount of parameters and calculation is greatly reduced compared with the ordinary residual module.…”

Section: Lightweight Modulementioning

confidence: 99%

See 1 more Smart Citation

Lightweight human pose estimation with attention mechanism

Chu

Dong

et al. 2023

Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022)

View full text Add to dashboard Cite

There are certain inevitable challenges in human pose estimation tasks based on deep learning methods, such as large amount of network parameters and high computational complexity. This paper proposes a lightweight network to reduce the scale of model parameters and computational complexity, meanwhile improve the accuracy of the human pose estimation task. The new method takes the high-resolution networks HRNet-32 as the basic framework and replaces the basic module with the MBConv lightweight module. The attention mechanism is incorporated into the network to model the context information, so as to improve the perception ability and the feature extraction ability of the module and improve the accuracy of human pose estimation. The experimental results on COCO2017 show that the proposed network can detect human key points with high precision even when the amount of parameters is reduced by 56%, which verifies that the proposed method has good lightweight performance.

show abstract

Section: Lightweight Modulementioning

confidence: 99%

“…Human pose estimation first appeared in 1980. The early methods are most model-based [4]. For example, [5] uses the Body Plan (BP) method to learn a series of human features and realize human pose estimation in complex environments.…”

Section: Introductionmentioning

confidence: 99%

Lightweight human pose estimation with attention mechanism

Chu

Dong

et al. 2023

Fourteenth International Conference on Graphics and Image Processing (ICGIP 2022)

View full text Add to dashboard Cite

show abstract

“…With the growing popularity of convolutional neural networks (CNNs), recent work on face-based age estimation has used these networks as a backbone ( Shen et al, 2018 ; Dagher and Barbara, 2021 ; Sharma et al, 2022 ; Zhang and Bao, 2022 ). Most of these works improve the learning ability of the network by increasing the number of layers of convolutional layers ( Dornaika et al, 2020 ; Yi, 2022 ) and improving the structure of the network. However, as convolutional networks continue to improve, the potential of CNN-based facial age estimation models has been exploited, and the increasing number of network model parameters has raised the cost of training.…”

Section: Introductionmentioning

confidence: 99%

Face-based age estimation using improved Swin Transformer with attention-based convolution

et al. 2023

View full text Add to dashboard Cite

Recently Transformer models is new direction in the computer vision field, which is based on self multihead attention mechanism. Compared with the convolutional neural network, this Transformer uses the self-attention mechanism to capture global contextual information and extract more strong features by learning the association relationship between different features, which has achieved good results in many vision tasks. In face-based age estimation, some facial patches that contain rich age-specific information are critical in the age estimation task. The present study proposed an attention-based convolution (ABC) age estimation framework, called improved Swin Transformer with ABC, in which two separate regions were implemented, namely ABC and Swin Transformer. ABC extracted facial patches containing rich age-specific information using a shallow convolutional network and a multiheaded attention mechanism. Subsequently, the features obtained by ABC were spliced with the flattened image in the Swin Transformer, which were then input to the Swin Transformer to predict the age of the image. The ABC framework spliced the important regions that contained rich age-specific information into the original image, which could fully mobilize the long-dependency of the Swin Transformer, that is, extracting stronger features by learning the dependency relationship between different features. ABC also introduced loss of diversity to guide the training of self-attention mechanism, reducing overlap between patches so that the diverse and important patches were discovered. Through extensive experiments, this study showed that the proposed framework outperformed several state-of-the-art methods on age estimation benchmark datasets.

show abstract