Model generation method and device, object classification method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses a model generation method and device, an object classification method and device, electronic equipment and a storage medium. The model generation method comprises the steps of acquiring a to-be-trained classification model and a plurality of unlabeled objects, wherein the to-be-trained classification model comprises a classification prediction module and a loss function determination module; inputting each unlabeled object into a classification prediction module, and determining a pseudo classification result of each unlabeled object according to each unlabeled prediction result output by the classification prediction module; and inputting each unlabeled prediction result and the corresponding pseudo classification result into a loss function determination module, adjusting network parameters in a classification prediction module according to an output result of the loss function determination module, and generating an object classification model. According to the technical scheme provided by the embodiment of the invention, the model iteration speed can be increased and the model classification performance can be improved in a mode of determining the pseudo classification result of the unlabeled object online in real time in the model iteration process.

Description

technical field [0001] The embodiments of the present disclosure relate to the field of computer application technology, and in particular, to a model generation method, an object classification method, a device, an electronic device, and a medium. Background technique [0002] Semi-supervised learning (Semi-Supervised Learning, SSL) has a good application in the field of image classification, and its specific implementation process is: based on the labeled sample set, the original classification model is trained to obtain the image classification model; based on the image classification model, the The unlabeled sample set is predicted, and the prediction result of the unlabeled sample with a relatively high confidence in each prediction result is used as the pseudo-label of the unlabeled sample, and the unlabeled sample and its pseudo-label are added to the labeled sample as the labeled sample. sample set; iteratively execute the above process based on the updated labeled s...

AI Technical Summary

Problems solved by technology

[0003] However, the generation of image classification models based on SSL has the following disadvantages: each update of the marked sample set will lead to re-iteration of the image classification model, the entire process cycle is longer, and the time cost is higher; Pseudo-labels are always invariant, which means that the classification performance of the resulting image classification model will be seriously affected in the case of false-prediction of pseudo-labels

Images