Image classification identification method and device based on adaptive dynamic convolutional network, and computer equipment

Abstract

The invention relates to the field of graph classification and recognition, in particular to an image classification and recognition method and device based on a self-adaptive dynamic convolutional network and computer equipment, and the method comprises the steps: obtaining a to-be-detected image, inputting the to-be-detected image into a preprocessing block, and obtaining a shallow feature graph and graph parameter information of the image; combining the image parameter information obtained after preprocessing with the to-be-detected image, and inputting the combined image parameter information and the to-be-detected image into an adaptive dynamic convolutional network of a backbone network to obtain image global features; wherein the adaptive dynamic convolution is to select a convolution kernel with a corresponding shape according to the corresponding parameter information; inputting an image shallow layer feature map obtained after preprocessing into a branch network, and extracting local features of the to-be-detected image; and carrying out feature fusion on the local features and the global features, inputting the fused features into a classification network, and outputting classification identification information of the to-be-detected image. According to the method, the calculation cost required for image classification and recognition is low, the precision is high, and the applicability of related products is high.

Description

technical field [0001] The invention belongs to the field of image classification and recognition, and in particular relates to an image classification and recognition method, device and computer equipment based on an adaptive dynamic convolution network. Background technique [0002] The purpose of image classification and recognition technology is to build a deep learning network model, output various information of the image after the input image passes through the deep learning network; widely apply those tasks based on image classification and recognition, such as the field of face recognition, the field of clothing image recommendation , accurate advertising push field, clothing matching recommendation, game film and television and other fields, is an active research topic in computer vision. [0003] The classic image classification recognition algorithm consists of two continuous but relatively independent stages: image feature extraction and image classification rec...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the present invention provides an image classification and recognition method, device and computer equipment based on an adaptive dynamic convolution network for the problems of insufficient expressive ability and redundant parameters caused by the uniform use of 3×3 rectangular convolution. , the global features of the image can be better obtained through the adaptive dynamic convolution network, and the network branch based on the Transformers block of the self-attention mechanism is added to the network to obtain the characteristics of the local position of the image, combined with the previous dynamic convolution The global features of the backbone network are fused, which further enhances the image feature extraction ability of the model, and effectively improves the accuracy of image classification and feature recognition

Images