Model training method and device for image classification and storage medium

Abstract

The invention discloses a model training method and device for image classification and a storage medium, and is used for solving the technical problem that a model obtained by an existing model training method cannot achieve a better image classification effect. The method comprises the steps of obtaining a visual feature vector of a sample picture; extracting a shallow semantic feature and a deep semantic feature in the visual feature vector based on a preset algorithm, and integrating the shallow semantic feature and the deep semantic feature to obtain a joint semantic feature; performing semantic space alignment on the joint semantic features to obtain a semantic alignment loss function; reconstructing the visual features, and determining an auto-encoder loss function according to the reconstructed visual features; and determining a target function training neural network model based on the semantic alignment loss function, the auto-encoder loss function and a preset parameter regular term. According to the method, the discrimination of the semantic embedding space is improved, and the domain bias problem of the zero sample learning model is relieved.

Description

technical field [0001] The present application relates to the technical field of computer vision, and in particular to a model training method, device and storage medium for image classification. Background technique [0002] With the widespread use of deep learning model frameworks, supervised learning has achieved many outstanding results in the field of image recognition. The deep learning model can continuously improve the recognition accuracy of the model through sufficient training. However, the existing supervised image recognition methods can only recognize the categories that have appeared in the data set. In most practical application scenarios, it takes a lot of time to mark a large amount of data. To solve this problem, the researchers proposed Zero-shot learning is used to identify categories that do not appear in the training set, and zero-shot learning aims to classify unseen categories through the knowledge learned in visible categories. [0003] Currently,...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a model training method, device and storage medium for image classification, to solve the problem that the model trained by the existing model training method for image classification has poor effect in image classification technical problem

Images