Facial Expression Recognition Based on Multi-Channel Attention Residual燦etwork

Abstract

For the problems of complex model structure and too many training parameters in facial expression recognition algorithms, we proposed a residual network structure with a multi-headed channel attention (MCA) module. The migration learning algorithm is used to pre-train the convolutional layer parameters and mitigate the overfitting caused by the insufficient number of training samples. The designed MCA module is integrated into the ResNet18 backbone network. The attention mechanism highlights important information and suppresses irrelevant information by assigning different coefficients or weights, and the multi-head structure focuses more on the local features of the pictures, which improves the efficiency of facial expression recognition. Experimental results demonstrate that the model proposed in this paper achieves excellent recognition results in Fer2013, CK+ and Jaffe datasets, with accuracy rates of 72.7%, 98.8% and 93.33%, respectively.

Convolutional Neural Network–Bidirectional Gated Recurrent Unit Facial Expression Recognition Method Fused with Attention Mechanism

“…Furthermore, our method outperforms the fusion of local binary pattern-based facial expression images with the original image proposed by Sun et al [42] by 0.76%. On the JAFFE dataset, our method achieves a 2.18% improvement over the approach presented by Shen et al [43], which combines the ResNet18 network structure with a multi-head channel attention mechanism. Overall, our approach consistently delivers the best FER recognition results across all three datasets, thanks to the combination of BiGRU and the attention mechanism in BGA-Net, enabling the model to focus on crucial facial expression regions.…”

Virtual Human: A Comprehensive Survey on Academic and Applications

“…This technology has been successfully commercialized and widely used in film and game production. Awan et al proposed a customised convolutional neural network for facial emotional expression classification with a focus on improving classification accuracy [34].Zhao et al proposed a deep block network for facial expression recognition and migration, especially in complex contexts [35].Shen et al introduced a multi-channel attentional residual network based facial expression recognition method with a focus on improving classification accuracy.The focus is on improving the accuracy of recognition [36].…”

Automatic polyp image segmentation and cancer prediction based on deep learning

“…Our proposed SCA module ( 36 ), with a general design idea similar to the architecture proposed by Fu et al. ( 37 ), integrates spatial and channel attention integration modules into an improved U-net network structure.…”

“…Our proposed SCA module (36), with a general design idea similar to the architecture proposed by Fu et al (37), integrates spatial and channel attention integration modules into an improved U-net network structure. The SCA module combines spatial and channel attention mechanisms to get comprehensive attention mechanism information.…”