Multimodal data subspace clustering method based on global consistency and local topology

Abstract

The invention provides a multimodal data subspace clustering method based on global consistency and local topology. The method comprises obtaining a Laplacian matrix corresponding to each piece of modal data, establishing a multimodal data subspace clustering model according to the Laplacian matrixes, obtaining a self-expression matrix corresponding to each piece of modal data through the multimodal data subspace clustering model, selecting the first self-expression matrixes from all the self-expression matrixes of the various pieces of modal data, and clustering the first self-expression matrixes to obtain a clustering result. The multimodal data subspace clustering method based on global consistency and local topology is capable of obtaining better clustering performance and enhancing the robustness.

Description

technical field [0001] The invention relates to the field of computers, in particular to a multi-modal data subspace clustering method based on global consistency and local topology. Background technique [0002] With the development of science and technology and the increasing popularity of the Internet, the collection of data in modern society has become easier and easier, and the amount of data is increasing day by day. At the same time, data is becoming more and more diverse, especially various multimodal data more and more common. Learning methods based on multi-modal data have also received more and more attention and research. Compared with single-modal data, multi-modal data can provide more and more complex information, so learning based on multi-modal data Models generally perform better and have better statistical properties. [0003] In the field of multimodal learning, multimodal data clustering has received extensive attention and development due to its abili...

AI Technical Summary

Problems solved by technology

[0004] However, although some current methods can improve the clustering performance of multimodal data to a certain extent, how to better mine and utilize information such as correlations and differences between different modalities still faces great challenges.

Images