Image recognition model generation method and device, computer equipment and storage medium

Abstract

The invention relates to an image recognition model generation method and device, computer equipment and a storage medium. The method comprises the steps of obtaining a sample image set; wherein the sample image set comprises a plurality of sample image subsets of which the number of images is sequentially decreased, and the plurality of sample image subsets comprise the same number of image categories; training a to-be-trained image recognition model according to the sample image set to obtain a loss value of the to-be-trained image recognition model; wherein the to-be-trained image recognition model comprises a plurality of branch neural networks; wherein the loss value comprises a target classification loss value and a classification loss value, the target classification loss value is aloss value of the model for the sample image set, and the classification loss value is a loss value of the branch neural network for the corresponding sample image subset; and adjusting model parameters according to the loss value until the loss value is lower than a preset threshold. According to the invention, the image types with a small number of images in the training process can be fully trained, and the effect of image recognition model generation is improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular, to a method, apparatus, computer equipment and storage medium for generating an image recognition model. Background technique [0002] In deep learning, image recognition technology has made tremendous progress. However, these advances are inseparable from large-scale datasets, such as ImageNet, COCO, etc. Usually, these large-scale datasets are class-balanced; but in real-world scenarios, the data we can obtain usually follows a long-tailed distribution, that is, a small number of classes contain a lot of image data, while most classes contain Image data is less. [0003] Using this kind of data that conforms to the long-tailed distribution to train the neural network, the result is usually that the neural network can identify a small number of categories with more image data, and identify most categories with less image data. The accuracy of the i...

AI Technical Summary

Problems solved by technology

[0003] Using this long-tail distribution data to train the neural network, the result is usually that the neural network can recognize a small number of categories that contain more image data, and recognize most categories that contain less image data. The accuracy of the image recognition model is poor; it can be seen that if the long-tail distribution characteristics are ignored in the generation of the image recognition model, the performance of the image recognition model will be greatly reduced in actual use.

[0004] Therefore, through the existing image recognition model generation method, the recognition effect of the obtained image recognition model is still poor

Images