Feature extraction model training and feature extraction methods and devices

CN115880545BActive Publication Date: 2026-05-26BEIJING IQIYI TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING IQIYI TECH CO LTD
Filing Date
2022-12-13
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing image retrieval algorithms separate feature extraction from feature aggregation, resulting in high algorithm complexity and low efficiency.

Method used

A feature extraction model training method is adopted, which constructs a feature extraction model by using attention mechanism to enhance and aggregate features through the local feature extraction layer, feature enhancement layer and global feature extraction layer in the initial model.

Benefits of technology

It achieves end-to-end global feature extraction, which improves feature extraction efficiency, reduces algorithm complexity, and suppresses irrelevant background interference and background noise in local features, thereby enhancing the representational power and richness of features.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115880545B_ABST
    Figure CN115880545B_ABST
Patent Text Reader

Abstract

This invention relates to a feature extraction model training and feature extraction method and apparatus, comprising: inputting a training image set into an initial model; extracting several local features from the training images by a local feature extraction layer; enhancing the several local features using an attention mechanism by a feature enhancement layer to obtain several enhanced local features; a global feature extraction layer aggregating features based on the several enhanced local features to obtain global features; and a classifier obtaining predicted classification parameters for the training images based on the global features. The model parameters of the initial model are adjusted according to the label parameters and predicted classification parameters of the training images to obtain a trained classification model. A feature extraction model for extracting global features is constructed based on the local feature extraction layer, feature enhancement layer, and global feature extraction layer in the classification model. This provides an end-to-end global feature extraction scheme, reducing algorithm complexity.
Need to check novelty before this filing date? Find Prior Art