Small sample image recognition method based on deep learning

Abstract

The invention relates to a small sample image recognition method based on deep learning. The method comprises the following steps of 1, dividing a training set; 2, generating a noise image; 3, pre-training a prototype space discrimination network; 4, training a deception image generation network; 5, training a prototype space discrimination network; 6, repeating the step 4 and the step 5 for crossiteration training until preset iteration times are reached or the accuracy is not improved any more; 7, performing image category recognition. According to the method, on the premise that a trainedmodel is not changed, by means of a few labeled samples of each class, through generalization of the rare classes, new classes which are not seen in the training process are recognized, extra trainingis not needed, and the image recognition accuracy is high.

Description

Technical field [0001] The invention belongs to the technical field of image recognition, and relates to a small sample image recognition method based on deep learning. More specifically, the present invention relates to a deep learning small sample image recognition method based on the idea of ​​generating confrontation networks and prototypes. Background technique [0002] Deep learning has been widely used in various fields to solve various problems, such as image recognition problems, which can often achieve high accuracy. However, deep learning is a "data-hungry" technology that requires a large number of labeled samples to function. But in reality, many problems are that there are not so many annotated images, and the cost of obtaining annotated images is also very high, such as in the medical field and security field. With the emergence of more application scenarios, we are increasingly facing the problem of insufficient sample numbers. Therefore, when the amount of anno...

AI Technical Summary

Problems solved by technology

The current scenario of the small sample problem, that is, the problem faced by the small sample problem is: without changing the trained model, we can only generalize these rare categories with the help of a few labeled samples of each category, and identify the training process. Never-before-seen new classes without additional training

Images