Parallel Convolutional Networks for Image Recognition via a Discriminator

Yang, Shiqi; Peng, Gang

doi:10.1007/978-3-030-20887-5_38

Cited by 2 publications

(3 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the single network structure, the parallel network structure can extract more abundant feature information to improve the generalization ability of the model. Therefore, it is widely used in the fields of object classification [ 33 , 34 ], object recognition [ 35 , 36 ], object detection [ 37 ], and so on.…”

Section: Related Workmentioning

confidence: 99%

“…Chowdhury et al [ 35 ] applied Billinear CNNs to face recognition and showed substantial improvements over the standard CNN. Yang et al [ 36 ] proposed the D-PCN framework consisting of two parallel CNNs, a discriminator, and an extra classifier which takes integrated features from parallel networks and gives a final prediction. Zhang et al [ 37 ] organized deep and shallow CNNs in parallel structures, realizing the simultaneous detection of large and small objects.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Image-Based Pain Intensity Estimation Using Parallel CNNs with Regional Attention

Liang

et al. 2022

Bioengineering

View full text Add to dashboard Cite

Automatic pain estimation plays an important role in the field of medicine and health. In the previous studies, most of the entire image frame was directly imported into the model. This operation can allow background differences to negatively affect the experimental results. To tackle this issue, we propose the parallel CNNs framework with regional attention for automatic pain intensity estimation at the frame level. This modified convolution neural network structure combines BlurPool methods to enhance translation invariance in network learning. The improved networks can focus on learning core regions while supplementing global information, thereby obtaining parallel feature information. The core regions are mainly based on the tradeoff between the weights of the channel attention modules and the spatial attention modules. Meanwhile, the background information of the non-core regions is shielded by the DropBlock algorithm. These steps enable the model to learn facial pain features adaptively, not limited to a single image pattern. The experimental result of our proposed model outperforms many state-of-the-art methods on the RMSE and PCC metrics when evaluated on the diverse pain levels of over 12,000 images provided by the publicly available UNBC dataset. The model accuracy rate has reached 95.11%. The experimental results show that the proposed method is highly efficient at extracting the facial features of pain and predicts pain levels with high accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Image-Based Pain Intensity Estimation Using Parallel CNNs with Regional Attention

Liang

et al. 2022

Bioengineering

View full text Add to dashboard Cite

show abstract

“…For breast cancer image classification, convolution neural network and recurrent neural network are modeled in parallel structure [9] to find the more number of features from the images. The two convolution neural networks [10] are arranged in a parallel architecture to improve the feature extraction capability. In a COVID-19 screening system [11], the chest X-ray images are analyzed by designing the dilated CNN in a parallel manner.…”

Section: Introductionmentioning

confidence: 99%

Multi-Feature Integrated Concurrent Neural Network for Human Facial Expression Recognition

Dhivyaa¹,

Dhivyaa²,

Nithya³

et al. 2022

Journal of Internet Technology

View full text Add to dashboard Cite

<p>Facial expression helps to communicate between the people for conveying abundant information about human emotions. Facial expression classification is applied in various fields such as remote learning education, medical care, and smart traffic. However, due to the complexity and diversity of the facial emotions, the present facial expression recognition model causes a low recognition rate and it is hard to extract the precise features that are related to facial expression changes. In order to overcome this problem, we proposed Multi-feature Integrated Concurrent Neural Network (MICNN) which is significantly different from the single neural network architectures. It aggregates the prominent features of facial expressions by integrating the three kinds of networks such as Sequential Convolutional Neural Network (SCNN), Residual Dense Network (RDN), and Attention Residual Learning Network (ARLN) to enhance the accuracy rate of facial emotions detection system. Additionally, Local Binary Pattern (LBP) and Principal Component Analysis (PCA) are applied for representing the facial features and these features are combined with the texture features identified by the Gray-level Co-occurrence Matrix (GLCM). Finally, the integrated features are fed into softmax layer to classify the facial images. The experiments are carried out on benchmark datasets by applying k-fold cross-validation and the results demonstrate the superiority of the proposed model.</p> <p> </p>

show abstract

Parallel Convolutional Networks for Image Recognition via a Discriminator

Cited by 2 publications

References 25 publications

Image-Based Pain Intensity Estimation Using Parallel CNNs with Regional Attention

Image-Based Pain Intensity Estimation Using Parallel CNNs with Regional Attention

Multi-Feature Integrated Concurrent Neural Network for Human Facial Expression Recognition

Contact Info

Product

Resources

About