Image classification method and system based on meta-learning and memory network

Abstract

The invention discloses an image classification method and system based on meta-learning and memory network. Firstly, the original feature representation of the image is obtained by learning; a memory network module is set, and each memory block in the memory network module is correspondingly stored with meta-knowledge of a corresponding category. ; Calculate the original feature representation of the image with the memory block to obtain the read parameters, and use the read parameters to obtain the final feature representation of the image from the memory block; map the final feature representation of the image to all memory blocks, and calculate its corresponding value in each memory block The probability value on the category, according to the size of the probability value to judge the category it belongs to. The present invention constitutes a memory network module by designing memory blocks corresponding to categories one by one, each memory block corresponds to the meta-knowledge of the corresponding category, and at the same time learns the meta-knowledge information between categories through the mode of sharing the memory blocks, so that when similar images pair Its operation plays an auxiliary role while suppressing the performance of other classes of images on this class to achieve better predictions.

Description

technical field [0001] The invention relates to the technical field of image recognition and classification, in particular to an image classification method and system based on meta-learning and memory networks. Background technique [0002] With the arrival and improvement of the era of big data and high-performance computing resource technology, deep learning has pushed the development of artificial intelligence to a new stage. Due to the outstanding achievements of deep learning in various fields, the current algorithm based on deep learning has become The mainstream method of research in the field of artificial intelligence, computer vision research is one of the important components of artificial intelligence research. Among them, pictures, as a common visual medium, are filled in every corner of the Internet age. With their simplicity and clarity, pictures play an important role in the process of information transmission. Especially with the popularity of the web age,...

AI Technical Summary

Problems solved by technology

However, this point is often ignored in traditional methods, or this feature is not well utilized, which leads to no direct sharing of information between the same type of pictures, but only in an indirect way.

The disadvantages of this method include: first, the model converges slowly, and it takes longer to train the network, which undoubtedly increases the calculation cost; second, the performance of the model is reduced to a certain extent, making the performance of the model less Maximize

Images