Zero sample learning method and system based on semantic attribute attention redistribution mechanism

Abstract

The invention discloses a zero sample learning method and system based on a semantic attribute attention redistribution mechanism, and the method comprises the steps: (1) building a neural network model based on the semantic attribute attention redistribution mechanism; (2) redistributing the weight between the semantic features by using the attention of the semantic attribute space; (3) traininga neural network model by using the image data set with the label; (4) calculating the similarity between the weighted semantic features of the images and the semantic prototypes of the unknown classes, calculating the similarity between the hidden layer features and the hidden layer feature prototypes of the unknown classes, and adding the two similarities to obtain the similarity between the test image and each unknown class; and (5) sorting according to the similarity with the types, and the type with the maximum similarity is selected as the type prediction of the image. According to the method, in the training process of zero sample learning, the semantic space and the hidden layer space can be more closely linked, and a joint classification result combining the two spaces is more robust.

Description

technical field [0001] The invention relates to the field of zero-sample learning classification systems, in particular to a zero-sample learning method and system based on a semantic attribute attention redistribution mechanism. Background technique [0002] In recent years, object classification, as an important branch in the field of computer vision, has attracted the attention of researchers from industry and academia. Benefiting from the rapid development of deep learning technology, the supervised object classification task has made great progress, but at the same time, there are some limitations in the training method under this supervised condition. In supervised classification, each class needs enough labeled training samples. In addition, the learned classifier can only classify instances belonging to the classes covered by the training data, lacking the ability to handle previously unseen classes. In practical applications, there may not be enough training sampl...

AI Technical Summary

Problems solved by technology

However, these methods essentially consider that all attributes are equally important in the classification process, while ignoring their different distributions

Images