Training method of image label classification network, image label classification method and equipment

Abstract

The invention discloses a training method of an image label classification network, an image label classification method and equipment, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining a sample image; performing feature extraction on the sample image through a feature extraction network to obtain a sample feature map output by the feature extraction network; inputting the sample feature map into a graph network classifier to obtain a sample label classification result output by the graph network classifier, with the graph network classifier being constructed based on a target graph network, graph nodes in the target graph network corresponding to image labels, and edges between different graph nodes being used for representing co-occurrenceprobabilities between different image labels; and training a feature extraction network and a graph network classifier according to an error between the sample label classification result and the sample image label. In the embodiment of the invention, when the graph network classifier is utilized to classify the labels, fusing the relevance between different image labels so that the image label classification efficiency and accuracy can be improved.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Benefits of technology

This invention provides an improved method that uses both neural networks with convolutional layers or other techniques like histograms to extract relevant characteristics from images without requiring training data. By doing this, more accurate results may be obtained compared to traditional methods such as thresholding and clustering algorithms.

Problems solved by technology

The technical problem addressed by this patented technique relates to improving object recognition performance when performing multilabel categorization on large amounts of data with many similar attributes or categories simultaneously without sacrificing precision due to overfitting during training.

Images