Fine classification method and system based on graph network multi-granularity feature learning

Abstract

The invention belongs to the field of computer vision and pattern recognition, relates to a fine classification method and system based on graph network multi-granularity feature learning and aims tosolve the problem of low image fine classification accuracy due to insufficient utilization of a target multi-granularity level relationship in the prior art. The method comprises the steps of: constructing a multi-granularity level relationship graph based on an obtained to-be-classified image; extracting the feature of each granularity level in the multi-granularity level relationship graph through a multi-granularity level feature extraction network; carrying out level relationship embedding on each granularity level feature in a multi-granularity level feature set; and obtaining a prediction category of each granularity level through a classifier. According to the method and system, a graph neural network is used for learning the semantic relation between the multi-granularity levels of an image, so that feature learning of all granularities is improved in a common promotion mode; the feature extraction network is composed of a main network and three branch networks, so that a model parameter quantity is reduced while high precision is achieved.

Description

technical field [0001] The invention belongs to the field of computer vision and pattern recognition, and in particular relates to a fine classification method and system for multi-granularity feature learning based on graph network. Background technique [0002] Fine classification is different from traditional classification tasks, such as distinguishing the category of cars, which need to distinguish its subcategories, such as the year of the car. In recent years, due to the great application value of this task, it has received extensive attention in both academic and industrial fields. Objects naturally have multi-grained category hierarchies. The higher levels correspond to categories with broad meanings, while the meanings of categories in lower levels are more refined, such as figure 2 As shown in the figure, it is a schematic diagram of multi-granularity category classification using automobile classification as an example. There are three granularity levels in the ...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned problems in the prior art, that is, the prior art does not utilize the multi-granularity hierarchical relationship of the target insufficiently, so that the accuracy of fine image classification is low, the present invention provides a fine classification based on multi-granularity feature learning based on graph network method, the fine classification method includes:

Images