Zero-sample image recognition method and system based on generative adversarial network

Abstract

The invention discloses a zero-sample image recognition method and system based on a generative adversarial network. The method comprises the steps: obtaining a training image sample with annotation information and a test image sample without annotation information; constructing a generative adversarial network model, wherein the generative adversarial network model comprises a semantic feature generator, a visual feature generator, a semantic discriminator and a visual discriminator; constructing a multi-objective loss function comprising a cyclic consistency loss function, an adversarial loss function of a semantic discriminator, an adversarial loss function of a visual discriminator and a classification loss function of the semantic discriminator; taking the training image sample as theinput of a generative adversarial network model, carrying out the iterative training of the generative adversarial network model based on a multi-objective loss function, and obtaining a trained generative adversarial network model; and inputting the test image sample into the trained generative adversarial network model to obtain an identification result. According to the invention, the sketch without annotation information can be identified, and the precision of zero sample identification is high.

Description

technical field [0001] The invention relates to the field of image recognition based on weak / semi-supervision, in particular to a zero-sample image recognition method and system based on a generative confrontation network. Background technique [0002] The concept of zero-shot learning (Zero-shot Learning, ZSL) was first proposed by H. Larochelle et al. in 2008. It is mainly used to solve the problem of how to deal with unknown new objects when labeled training samples are not enough to cover all object classes. The problem of correct classification and identification of objects. If a classifier is learned on the training set and applied to the test sample set according to the traditional supervised learning method, the classification effect will be poor due to the different sample distributions of the two domains. This image recognition problem is called zero-shot recognition. [0003] Zero-shot recognition requires only labeled samples of known categories to predict unkn...

AI Technical Summary

Problems solved by technology

In this case, data from both source and target classes should be considered, so generalized zero-shot settings have been introduced in recent years. However, the accuracy of zero-shot recognition based on generalized zero-shot learning is much lower than that based on traditional zero-shot learning. Recognition accuracy

Therefore, the current generalized zero-shot recognition method has the problem of low recognition accuracy

Images