| CPC G06V 40/171 (2022.01) [G06T 7/73 (2017.01); G06V 40/166 (2022.01)] | 20 Claims |
|
1. A computer-implemented method for training a multi-task recognition model, comprising:
obtaining a first set of sample images, a second set of sample images, and a third set of sample images, wherein the first set of sample images comprise a plurality of sample images that are configured to provide feature-independent facial attributes, the second set of sample images comprise a plurality of sample images that are configured to provide feature-coupled facial attributes, and the third set of sample images comprise a plurality of sample images that are configured to provide facial attributes of face poses;
training an initial feature-sharing model based on the first set of sample images to obtain a first feature-sharing model with a loss value less than a preset first threshold;
training the first feature-sharing model based on the first set of sample images and the second set of sample images to obtain a second feature-sharing model with a loss value less than a preset second threshold;
obtaining an initial multi-task recognition model by adding a feature decoupling model to the second feature-sharing model; and
training the initial multi-task recognition model based on the first set of sample images, the second set of sample images, and the third set of sample images to obtain a trained multi-task recognition model with a loss value less than a preset third threshold.
|