Abstract
In order to achieve high-efficiency and high-precision multi-image classification tasks, a multi-attention ghost residual fusion network (MAGR) is proposed. MAGR is formed by cascading basic feature extraction network (BFE), ghost residual mapping network (GRM) and image classification network (IC). The BFE uses spatial and channel attention mechanisms to help the MAGR extract low-level features of the input image in a targeted manner. The GRM is formed by cascading 4 multi-branch group convolutional ghost residual blocks (MGR-Blocks). Each MGR-Block is cascaded by a dimension reducer and several ghost residual sub-networks (GRSs). The GRS integrates ghost convolution and residual connection, and the use of ghost convolution can significantly reduce parameters and achieve high-efficient classification. The GRS is a parallel convolution structure with 32 branches, which ensures that GRM has enough width to extract advanced features and extract as much feature information as possible, so as to obtain high-precision classification. The IC completes the aggregation of high-dimensional channel feature information, and then achieves a significant improvement in the classification accuracy of MAGR, by fusing the effective channel attention mechanism, global average pooling and SoftMax layer. Simulation experiment shows that MAGR has excellent classification capability while achieving high efficiency and lightweight. Compare with VGG16, the parameters of MAGR on CIFAR-10 is reduced by 94.8% while the classification accuracy is increased by 1.18%. Compare with MobileNetV2, the parameters of MAGR on CIFAR-100 is reduced by 33.9% while the classification accuracy is increased by 15.6%.
Highlights
Image classification is a technology that uses algorithms to determine the category of a given image
In order to improve the classification accuracy of the model, He [3] et al propose the ResNet residual network, which solves the gradient dispersion and explosion problems caused by network deepening through the residual connection structure
(2) The residual connection is introduced into the multi-branch group convolution ghost residual blocks (MGR-Blocks) to broaden the network width, and enhance the feature extraction ability, thereby improving the classification accuracy
Summary
Image classification is a technology that uses algorithms to determine the category of a given image. (2) The residual connection is introduced into the multi-branch group convolution ghost residual blocks (MGR-Blocks) to broaden the network width, and enhance the feature extraction ability, thereby improving the classification accuracy. MULTI-ATTENTION GHOST RESIDUAL FUSION NETWORK The structure of MAGR is shown in Fig., which uses a cascading structure, first extracts the basic feature information, extracts the advanced feature information, and outputs the classification results. The structure is helpful for the convolution layer to extract richer feature information from input X and improve classification accuracy of MAGR. The EAC attention module is responsible for strengthening the connection between the high-dimensional channel information that output by the GRM, which helps the model to further extract useful feature information without increasing the calculation cost. The feature vector composed of all feature points is sent to SoftMax layer to realize the final classification
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
