Zero-sample image classification method of adversarial network based on meta-learning

Abstract

The invention belongs to the technical field of image classification, and particularly relates to a zero-sample image classification method of an adversarial network based on meta-learning. The methoduses a meta-learning training mode in a zero-sample classification task, and simulates the learning task of zero-sample image classification in a training stage by inputting visual features and semantic features into a network in sequence. According to the method, the generation process of the visual features is completed, the alignment relation of different classifiers is guaranteed, meanwhile,knowledge obtained by tasks of each epinode is fully utilized, semantic classifiers are better trained under the supervision of the visual classifiers, and therefore the visual features and the semantic features which are closer to real distribution are synthesized, and the visual features and the semantic features which are closer to real distribution are obtained. A zero-sample image classification technology suitable for a real situation is designed. According to the method, the generalized zero-sample image classification capability can be more outstanding, the generalization capability ofthe model is improved, and the problem of domain offset generally existing in zero-sample learning is relieved.

Description

technical field [0001] The invention belongs to the technical field of image classification, and in particular relates to a zero-sample image classification method based on a meta-learning confrontation network. Background technique [0002] In recent years, machine learning has been widely used in natural language processing, computer vision, speech recognition and other fields. In the field of computer vision, image classification tasks are one of the most concerned and widely used tasks, and various classification techniques emerge in endlessly. , the performance is continuously improved. In machine learning tasks, the supervised learning method of classifying through a large number of manually labeled images is a traditional method of image classification and has been well applied in real life. However, it is not easy to collect enough samples for each category of images and label them in practice, and it will consume a lot of labor. It is not difficult to understand t...

AI Technical Summary

Problems solved by technology

However, due to the introduction of the variational lower bound of VAE, the generated visual features are easy to be distorted.

Images