Face attribute recognition model training method and device, face attribute recognition method and device

By designing a low-level feature extraction and multiple facial attribute recognition networks in a single network model and training it using a weighted triplet loss function, efficient and accurate recognition of multiple facial attributes is achieved. This solves the problems of high computational resource consumption and cumbersome recognition process in existing technologies, making it suitable for mobile device applications.

CN116030523BActive Publication Date: 2026-06-12THUNDERSOFT
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
THUNDERSOFT
Filing Date
2023-01-30
Publication Date
2026-06-12

Smart Images

  • Figure CN116030523B_ABST
    Figure CN116030523B_ABST
Patent Text Reader

Abstract

The application discloses a face attribute recognition model training method and device, and a face attribute recognition method and device. The face attribute recognition model training method comprises the following steps: obtaining a to-be-trained face image, and marking multiple face attribute information in the to-be-trained face image; performing feature extraction on the to-be-trained face image by using a bottom feature extraction network in a face attribute recognition model to obtain a bottom feature extraction result; performing feature extraction and recognition on the bottom feature extraction result by using multiple face attribute recognition networks in the face attribute recognition model respectively to obtain multiple face attribute recognition results; determining a loss value of each face attribute recognition result based on a preset loss function of each face attribute recognition network respectively, and updating parameters of the face attribute recognition model by using the loss value of each face attribute recognition result to obtain a trained face attribute recognition model. The face attribute recognition model can recognize multiple face attribute information simultaneously.
Need to check novelty before this filing date? Find Prior Art