Model training method and apparatus, face recognition method and apparatus, device, and storage medium

A model training method, performed by at least one processor of a computing device, the method comprising:

• obtaining training batch data, the training batch data comprising a sample face image;
• extracting an identity feature and an age feature of the sample face image by using a feature extraction module, which is implemented by using a neural network;
• determining a correlation coefficient corresponding to the training batch data according to the identity feature and the age feature of the sample face image in the training batch data;
• and
• performing decorrelated training of the identity feature and the age feature on the feature extraction module based on the correlation coefficient.

A model training apparatus, comprising:

• at least one memory configured to store program code;
• and
• at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising:
• obtaining code configured to cause at least one of the at least one processor to obtain training batch data, the training batch data comprising a sample face image;
• extraction code configured to cause at least one of the at least one processor to extract an identity feature and an age feature of the sample face image by using a feature extraction module, which is implemented by using a neural network;
• determining code configured to cause at least one of the at least one processor to determine a correlation coefficient corresponding to the training batch data according to the identity feature and the age feature of the sample face image in the training batch data;
• and
• training code configured to cause at least one of the at least one processor to perform decorrelated training of the identity feature and the age feature on the feature extraction module based on the correlation coefficient.