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

Abstract

The present application relates to an image recognition model generation method, device, computer equipment, and storage medium, including: obtaining a sample image set; the sample image set includes a plurality of sample image subsets in which the number of images decreases successively, and the plurality of sample image subsets all include The same number of image categories; according to the sample image set, the image recognition model to be trained is trained to obtain the loss value of the image recognition model to be trained; the image recognition model to be trained includes multiple branch neural networks; the loss value includes the target classification loss value and classification loss value, the target classification loss value is the loss value of the model for the sample image set, and the classification loss value is the loss value of the branch neural network for the corresponding sample image subset; adjust the model parameters according to the loss value until the loss value is lower than preset threshold. The application enables sufficient training of image categories with a small number of images in the training process, and improves the effect of image recognition model generation.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to an image recognition model generation method, device, computer equipment and storage medium. Background technique [0002] In deep learning, image recognition technology has made great progress. But these advances are inseparable from large-scale datasets, such as ImageNet, COCO, etc. Usually, these large-scale data sets are class-balanced; but in real-world scenarios, the data we can obtain usually follows a long-tail distribution, that is, a small number of classes contain a lot of image data, while most classes contain a lot of image data. Image data is less. [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 is poor; it can be seen t...

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