A semi-supervised classification method for feature distribution inconsistency and related device

Abstract

The application discloses a semi-supervised classification method for feature distribution inconsistency and a related device, relates to the technical field of data classification, and adopts an adversarial domain adaptation strategy and an improved mixup strategy to optimize a semi-supervised classification model in the method, and then corrects a classification probability prediction result of an unmarked sample based on class prototypes of each class of a marked data set and an unmarked data set, and then optimizes the locally optimized semi-supervised classification model based on the marked data set and the unmarked data set each having corresponding classification labels, to obtain a globally optimized semi-supervised classification model, which can accurately generate a classification probability prediction result and determine a classification label. The feature distribution inconsistent data used in the above scheme of the application only uses a small amount of labeled samples, and there is no need to ensure that the feature distribution of the labeled samples and the unmarked samples is consistent, thereby reducing the sample labeling cost and solving the problem of low classification accuracy in feature distribution inconsistent data.

Images