Image classification method and device, electronic equipment and storage medium

Abstract

The invention relates to an artificial intelligence technology, and discloses an image classification method, which comprises the following steps: acquiring an original image set which comprises an annotated image set and an unannotated image set, performing annotation guessing on images in the unannotated image set to obtain an annotated guessed image set, summarizing the annotated guessed image set and the annotated image set, obtaining an image training set, constructing a representation mixing layer in a preset image classification network to obtain a mixed image classification network, training the mixed image classification network by using the image training set to obtain a standard image classification network, and classifying images to be classified by using the standard image classification network to obtain an image classification result. The invention also relates to a block chain technology, and the image classification result can be stored in a node of a block chain. The invention further provides an image classification device, electronic equipment and a computer readable storage medium. According to the invention, the problem of low image classification accuracy can be solved.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to an image classification method, device, electronic equipment and computer-readable storage medium. Background technique [0002] After the advent of the era of deep learning, a series of breakthroughs have occurred in the field of image classification. However, this breakthrough is based on a large-scale labeled dataset. Large-scale labeled datasets are a luxury. In fields such as medical images, image annotation often takes a lot of time of domain experts. Cognitive differences among experts will also lead to labeling noise, and in order to eliminate this noise, more experts are needed for blind labeling. [0003] Using semi-supervised learning methods can reduce the labeling burden. Semi-supervised methods can use a large amount of unlabeled data and a small amount of labeled data to enhance the performance of the model. However, an important goal in...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides an image classification method, device, electronic equipment and computer-readable storage medium, the main purpose of which is to solve the problem of low image classification accuracy

Images