Image classification method, image classification device, storage medium and electronic equipment

Abstract

The invention provides an image classification method, an image classification device, a storage medium and electronic equipment, and relates to the technical field of artificial intelligence. The method comprises the following steps: extracting intermediate features of a to-be-processed image by utilizing a pre-trained image classification network; determining the similarity between the intermediate feature of the to-be-processed image and the reference features of each category, wherein each category is each image classification category associated with the image classification network; matching the similarity between the intermediate feature of the to-be-processed image and the reference feature of each category with predetermined similarity probability distribution of each category toobtain a classification result of the to-be-processed image, wherein the classification result comprises the step of determining that the to-be-processed image belongs to a target category in the categories, or determining that the to-be-processed image does not belong to the categories. According to the disclosure, the accuracy of image classification can be improved, and particularly, the misclassification situation for out-of-class images can be reduced.

Description

technical field [0001] The present disclosure relates to the technical field of artificial intelligence, and in particular to an image classification method, an image classification device, a computer-readable storage medium, and electronic equipment. Background technique [0002] With the development of deep learning technology and the application of large-scale data sets like ImageNet (a large image database for computer vision), image classification and recognition have achieved high accuracy. However, when the image classification algorithm is applied to the real life scene (open set), some images usually appear, which do not belong to any category in the training set, and these images are called out-of-class images; in the image classification of the open set scene , out-of-class images may be misclassified into the categories in the training set, affecting the accuracy of classification. [0003] In the prior art, by adjusting the probability threshold of image classi...

AI Technical Summary

Problems solved by technology

However, in this method, it is often difficult to determine an appropriate threshold: if the threshold is too low, the filtering ability is limited; if the threshold is too high, images of the correct category may be filtered out; and, because different categories have different degrees of difficulty in recognition, Different thresholds should be used for different categories, which increases the complexity of the algorithm

Images