Reward in image description model and construction method of image description model

Abstract

The invention relates to the technical field of image description, in particular to a reward in an image description model and a construction method of the image description model, and the construction method of the reward comprises the steps: obtaining label description of a test image and generation description of a preset image description model based on the test image; based on the label description and the generation description, calculating a reward of the n-tuple in the generation description; comparing the size relationship between the reward of the n-tuple and the first threshold value with the size relationship between the reward of each word in the n-tuple and the second threshold value so as to screen out the word with the reward to be increased in the generated description; and according to the label description and the reward of the n-tuple corresponding to the word with the reward to be increased, calculating the reward of the word with the reward to be increased. According to the method, higher rewards are given to words which are not frequently appeared to realize constraint, so that the problem of non-uniform word distribution can be well solved, more specific visual details of an image can be captured, and the description accuracy of the image can be improved.

Description

Technical field [0001] The present invention relates to the technical field of image description, in particular to a method for constructing a reward in an image description model and an image description model. Background technique [0002] The task of image description is a common task in daily life. Its purpose is to generate a natural language description that complies with grammatical rules to describe the content of the image based on the content of the image. This task can be applied to early childhood education, navigation and guidance in real life. [0003] The intersection of computer vision and natural language processing is the two major areas of artificial intelligence. Although both areas use similar artificial intelligence and machine learning methods for field research, there is still very little interaction between the two areas. However, in recent years, the fields of natural language processing and computer vision have made tremendous progress in analyzing and ...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the embodiment of the present invention provides a reward and image description model construction method in the image description model to solve the problem of low accuracy of image description

Images