Small sample picture classification model and method based on semantic auxiliary attention mechanism

Abstract

The invention discloses a small sample picture classification model and method based on a semantic auxiliary attention mechanism, and belongs to the field of small sample picture classification in computer vision. The system comprises a convolutional neural network, an extension model for zero sample picture classification, a spatial attention module and a semantic alignment module. The method comprises the following steps: selecting a training data set; constructing a network structure of the small sample picture classification model based on the semantic aided attention mechanism; preprocessing the training data, dividing the training data into a training set, a verification set and a test set, and subdividing each sub-data set into data packets including a support set and a test set; training a small sample picture classification model; and verifying the small sample picture classification model. According to the method, an attention mechanism and a multi-module learning principle are combined, the method is divided into two sub-modules, namely a spatial attention module and a semantic alignment module, the method can focus on a local area, and better small sample picture classification can be realized.

Description

technical field [0001] The invention belongs to the field of small-sample picture classification in computer vision, and in particular relates to a small-sample picture classification model and method based on a semantic-assisted attention mechanism. Background technique [0002] Few-shot learning aims to solve how to carry out effective machine learning in the case of few samples. Few-shot learning is closer to human learning mode and has high academic and industrial value. Firstly, small-sample learning helps to reduce the pressure of supervised data collection; secondly, small-sample learning helps to solve the learning problem of rare samples. Because small sample learning gets rid of the dependence on a large amount of labeled data to a certain extent, it has become one of the research hotspots in the field of artificial intelligence in recent years. [0003] Few-shot image classification is a sub-application problem of the small sample learning problem, which aims to...

AI Technical Summary

Problems solved by technology

[0007] Traditional embedding and measurement algorithms have fuzzy problems in feature embedding, which leads to deviations in the representation of class centers, which has a negative impact on classification tasks

This ambiguity problem is mainly because the traditional convolutional neural network structure focuses on areas that are easily affected by the external environment.

Images