Image classification method and system based on double attention mechanisms, and electronic equipment

Abstract

The invention discloses an image classification method and system based on double attention mechanisms and electronic equipment, and the method comprises the steps: calculating the attention weights of a feature map space dimension and a feature map channel dimension at the same time through an improved self-attention model, adding feature maps generated by the two attention mechanisms, and completing the construction of an end-to-end image classification network. The adaptive perception capability of the network to the salient region is improved, more accurate and robust image feature expression is realized, and the image classification performance is further improved.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image classification method, system and electronic equipment, in particular to an image classification method, system and electronic equipment based on a dual attention mechanism. Background technique [0002] Since the birth of deep learning, related technologies, especially those related to deep convolutional networks, have brought great changes and influences to the field of computer vision. The image classification method based on deep convolutional networks has become the mainstream method of current research. However, this method also has the following disadvantages: [0003] (1) Excessive reliance on training data. Image feature expression is the core content of image classification methods based on deep convolutional networks, and accurate and robust feature acquisition largely depends on the network's learning of massive data. The quantity and quality of data ...

AI Technical Summary

Problems solved by technology

[0004] (2) Limitations of the convolution mode

The essence of the convolution operation is to use a single sampling mode to filter a specific area. Although the deep convolutional network can realize the feature expression in the large-scale receptive field through multi-layer and multi-modal convolution operations, the singleness and adjacency of the sampling mode This limitation restricts the accurate expression of features of different scales by the convolutional network, and also leads to the weak correlation of the local representation of the final generated features at the overall image level, which cannot ensure that the local features with similar semantic content of the image have similar feature expression

[0005] (3) The classification recognition degree between feature map channels is different

Images