And searching reliable semi-supervised few-sample image classification method of abnormal data center

Abstract

The invention discloses a semi-supervised few-sample image classification method for searching a reliable abnormal data center. The method specifically comprises the following steps: dividing a data set; sampling a semi-supervised few-sample classification task from the training set; extracting feature representation of the few-sample classification task samples by using a neural network; searching a reliable abnormal data clustering center; optimizing various image prototypes by utilizing label-free data; classifying to-be-classified samples in the task by utilizing the prototype, calculatingcross entropy loss, and performing back propagation to update network parameters; performing iterative training to obtain an ideal feature extraction network; and completing a semi-supervised few-sample classification task. According to the method, the feature extractor suitable for few-sample classification is trained, so that the classifier can still obtain relatively ideal classification performance under the condition of extremely few training data. And label-free data is added during training, a reliable abnormal data center searching method is utilized, information of the label-free data is reasonably utilized, and the performance of the classifier is improved.

Description

technical field [0001] The invention belongs to the technical field of deep learning and image classification, and relates to an image classification method, in particular to a semi-supervised few-sample image classification method for finding reliable abnormal data centers. Background technique [0002] In recent years, deep learning has achieved great success in tasks such as computer vision, machine translation, and speech modeling by learning knowledge from a large amount of labeled data and training deep neural network models. However, training a deep neural network requires iterative training using a large amount of labeled data to achieve satisfactory results. In the case of insufficient amount of labeled data, traditional deep learning methods fail. [0003] To solve this problem, few-shot learning methods have become a hot spot of attention. The few-shot learning method uses the method of meta-learning to obtain general knowledge from the training data, so that th...

AI Technical Summary

Problems solved by technology

[0006] However, the existing methods assume that the cluster center of the interference data (abnormal data) is at the origin. This assumption is simple but unreasonable.

Images