Semi-supervised learning pseudo label assignment method based on clustering fusion

Abstract

The invention discloses a semi-supervised learning pseudo label assignment method based on clustering fusion, and the method comprises the steps: carrying out the semi-supervised learning of a convolutional neural network with a label-free data set, carrying out the pre-training of the neural network through employing labeled data and label-free data, and extracting data features through employinga trained network; assigning pseudo tags to N pieces of untagged data closest to the tagged data by using a nearest neighbor method; analyzing all the data information by using k-means clustering, and endowing clustered pseudo tags to the data which is not tagged; and continuously training the convolutional neural network by using the obtained label data and pseudo label data to obtain an optimalnetwork for label assignment. The method can be suitable for semi-supervised learning under deep learning in various fields; information of label-free data can be fully mined, and training data withricher content are provided for a network; the principle is clear and easy to understand, and codes are easy to implement.

Description

technical field [0001] The invention relates to the technical field of pseudo-label assignment of semi-supervised learning, in particular to a method for assigning pseudo-labels of semi-supervised learning based on cluster fusion. Background technique [0002] With the increasing development of deep learning, fully supervised learning using labeled data to train neural networks has achieved good results. However, in daily life, relying on manual labeling data often consumes a lot of human and financial costs, and unlabeled data is often easily obtained in large quantities. Therefore, in recent years, semi-supervised and unsupervised learning has attracted the attention of researchers. focus on. Semi-supervised learning is between supervised learning and unsupervised learning. It not only takes into account the accuracy of supervised learning, but also takes into account the practicability of unsupervised learning. It is a key issue in the field of pattern recognition and ma...

AI Technical Summary

Problems solved by technology

However, in daily life, relying on manual labeling data often consumes a lot of human and financial costs, and unlabeled data is often easily obtained in large quantities. Therefore, in recent years, semi-supervised and unsupervised learning has attracted the attention of researchers. focus on

Images