Training data enhancement method and device, computer equipment and storage medium

Abstract

The invention relates to the field of model training, in particular to a training data enhancement method and device, computer equipment and a storage medium, and the method comprises the steps: obtaining a training data set; inputting the training data set into a classification model for pre-training, and obtaining an original image and classification data which are wrongly classified; inputting the original image into a preset residual network to obtain features of the original image; calculating mutual information of the features according to the classification data, and screening false features of which the influence degree is greater than a preset value in the features according to the mutual information; performing data enhancement on the original image according to the false features to obtain a target image; and generating an enhanced training data set according to the target image, and retraining the classification model based on the enhanced training data set. According to the method and the device, errors of the model can be traced, features related to the prediction result can be searched, the original data set is enhanced, and the robustness of the model is improved.

Description

technical field [0001] The present application relates to the field of model training, and in particular, to a training data enhancement method, apparatus, computer equipment and storage medium. Background technique [0002] Classification methods based on convolutional neural networks currently show good performance on multiple tasks, but their generalization ability is still limited. In different jobs, the performance of the model may vary greatly, which affects the user's trust in the model. At present, to solve the problem of wrong model recognition results, most of them are solved by increasing the amount of training data. The model cannot be fundamentally improved, resulting in a lower model robustness. SUMMARY OF THE INVENTION [0003] The main purpose of the present application is to provide a training data enhancement method, device, computer equipment and storage medium, aiming to solve the problem of low robustness of the model caused by incorrect data that obv...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of this application is to provide a training data enhancement method, device, computer equipment, and storage medium, aiming to solve the problem of low robustness of the model caused by wrong data that obviously affects the model results in the training data

Images