Semi-supervised image classification method based on random region interpolation

Abstract

The invention discloses a semi-supervised image classification method based on random region interpolation, and the method comprises the steps: selecting a small number of images with real labels froma training set, and taking other remaining images as images without real labels; simultaneously sending the two types of images to a random region interpolation module; wherein the interpolation process is different, the image with the real label can directly generate a new augmented image through interpolation, but each image without the real label cannot be normally interpolated, so that high-confidence label information can be obtained through a teacher network to serve as a temporary label of each image without the real label, and then interpolation operation is carried out; and trainingthe network by using the new augmented image until the network model is trained to a preset number of times. Random region interpolation is carried out on two types of images at the same time, a new augmented image is generated for training a classification network, and the generalization performance of a training model is improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a semi-supervised image classification method based on random area interpolation. Background technique [0002] With the growth of social media and web services, tons of photos are uploaded every day. Labeling them manually for model training becomes less feasible. However, in a growing number of applications having ground truth labeled data is insufficient and unlabeled data is readily available. In order to solve the problem of learning in part of the data with real labels, semi-supervised learning is studied to effectively reduce the dependence on the data with real labels by using the data without real labels. [0003] Semi-supervised learning is a key issue in the field of pattern recognition and machine learning, and it is also a learning method that combines supervised learning and unsupervised learning. Semi-supervised learning uses a large amount of unlabeled ...

AI Technical Summary

Problems solved by technology

[0005]The purpose of the present invention is to overcome the problem that existing deep neural networks always tend to learn the most discriminative features to obtain high training accuracy, and may focus on not necessarily Important or unwanted areas, especially with limited supervision

Images