Information processing model generation method based on target attribute decoupling and related equipment

Abstract

The invention provides an information processing model generation method based on target attribute decoupling and related equipment, and the method comprises the steps of obtaining feature maps outputby a hidden layer, carrying out the coding of the feature maps through Hash codes, and obtaining coordinate values corresponding to all feature maps; clustering the feature maps according to the coordinate values to obtain a feature map group, respectively calculating orthogonal loss and / or inhibition loss corresponding to the feature graphs in each feature graph group, obtaining a total loss value of the model according to the calculated orthogonal loss and / or inhibition loss, adjusting model parameters by utilizing the total loss value of the model, and repeating the above steps until the training is completed, so as to obtain a generated information processing model. According to the method provided by the embodiment of the invention, the attribute coupling is reduced by mining the semantic attributes of the latent layer and constructing the orthogonal loss of the clustering group, and the cross coupling according to the attributes is reduced by performing intersection suppressionon the feature maps in the intersection region, so that the attribute coupling between the feature maps is reduced, and the generalization ability of the network is improved.

Description

technical field [0001] The present invention relates to the technical field of neural networks, in particular to an information processing model generation method and related equipment based on target attribute decoupling. Background technique [0002] Since Goodfellow proposed Generative Adversarial Network (GAN), it has achieved impressive performance in various attribute editing, such as expression editing, style transfer, hair color transformation, gender transformation, age transformation, etc. However, the semantic correlation produced by the feature map interaction in the generative network of GAN may hurt the generalization ability of the generative network. [0003] When GANs learn from large training datasets, feature maps are prone to be highly coupled to each other. However, the highly coupled information learned from the training dataset is difficult to apply to the test dataset due to the large variance in coupling between different identities and datasets. A...

AI Technical Summary

Problems solved by technology

[0006] In view of the deficiencies in the above-mentioned prior art, the purpose of the present invention is to provide users with an information processing model generation method and related equipment based on target attribute decoupling , to overcome the defect that the network structure in the prior art has poor generalization ability due to feature map coupling affecting the generation effect during attribute editing, resulting in poor generalization ability of the generation network

Images