Image multi-label classification method, system, device and readable storage medium

Abstract

The invention belongs to the field of image classification, and discloses an image multi-label classification method, system, equipment and readable storage medium. The method includes: S1: acquiring original images corresponding to each of the multi-labels to be classified, and generating a sample set; S2 : Obtain the initial deep convolutional neural network for image multi-label classification, and add a gate activation function layer to obtain the deep convolutional neural network; S3: Iteratively train the deep convolutional neural network through the sample set to obtain the saliency map corresponding to each label; S4: Select the saliency map corresponding to the preset required label, and extract the target from the corresponding original image through the saliency map; S5: Set the image to be generated, and transfer the target area to the image to be generated to obtain the target image; S6: Set The target image is added to the sample set, the preset number of iterations from S3 to S5 is iterated, and the image multi-label classification of the input image is performed through the final deep convolutional neural network. This method effectively improves the precision and accuracy of image multi-label classification.

Description

technical field [0001] The invention belongs to the field of image classification, and relates to an image multi-label classification method, system, equipment and readable storage medium. Background technique [0002] Image multi-label classification has always been a hot issue in the field of computer vision. With the rise and development of artificial intelligence technology, image multi-label classification methods based on deep learning, especially image multi-label classification using deep convolutional neural networks, have made significant progress. A breakthrough, its classification accuracy far exceeds the traditional machine learning method. However, due to the huge amount of model parameters based on deep convolutional neural networks, the results generally lack interpretability, which makes the results of image multi-label classification based on this method unreliable, which has become a bottleneck for the further development and application of deep learning. ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the shortcomings of insufficient high precision and low accuracy of image multi-label classification in the above-mentioned prior art, and provide a method, system, device and readable storage medium for image multi-label classification

Images