An image classification method and system based on enhanced small sample feature decoupling

By combining CNN and transformer with a method based on few-sample data augmentation and feature decoupling, the conflict between fine-grained and coarse-grained feature extraction in image classification is resolved, achieving efficient image recognition even with insufficient training samples and improving the accuracy of image classification.

CN116310495BActive Publication Date: 2026-07-07ZHONGGUOCHANGFENG ELECTROMECHANICAL TECH RES SHEJIY
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ZHONGGUOCHANGFENG ELECTROMECHANICAL TECH RES SHEJIY
Filing Date
2023-01-09
Publication Date
2026-07-07

Smart Images

  • Figure CN116310495B_ABST
    Figure CN116310495B_ABST
Patent Text Reader

Abstract

The specification discloses an image classification method and system based on enhanced small sample feature decoupling, aiming to solve the problem that fine-grained features and coarse-grained features cannot be effectively extracted to obtain sufficient local information and global information. The application comprises: based on the to-be-tested data, obtaining enhanced to-be-tested data through a small sample-based data enhancement model; obtaining the enhanced to-be-tested data through a multilayer perceptron and a first classifier; decoupling the enhanced to-be-tested data to obtain fine-grained features and coarse-grained features; connecting the fine-grained features and the coarse-grained features through a feature connector, and classifying based on the connected features through a trained second classifier to obtain a classification prediction result. The application can quickly extract fine-grained features and coarse-grained features, effectively solve the conflict between fine-grained feature extraction and coarse-grained feature extraction, improve the accuracy of image recognition, and solve the problem of insufficient training samples.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Small sample image increment classification method and device based on embedding enhancement and self-adaption

    CN114549894A

  • Improved visual Transform seabed sediment sonar image classification method based on transfer learning

    CN115170943A