Grassmann manifold domain self-adaption method based on symmetric matrix space subspace learning

Abstract

The invention relates to a domain self-adaption technology in the field of machine learning, and provides a Grassmann manifold domain self-adaption method based on symmetric matrix space subspace learning. In order to reduce the difference between the probability distribution of the source domain data and the target domain data, the method comprises the following steps of firstly establishing mapping from a Grassmann manifold to a symmetric matrix space, then mapping the Grassmann manifold matrix data of the source domain and the target domain to the symmetric matrix space, and constructing asubspace in the symmetric matrix space; subjecting the projection of the original data in the subspace to a mean value similarity criterion; establishing an objective function of the subspace learning, optimizing and solving the objective function to obtain the objective subspace, matching the projection probability distribution of the original data in the objective subspace on the objective subspace, that is, achieving the domain self-adaption of the original data through twice transformation from the Grubman manifold to the symmetric matrix space and then from the symmetric matrix space to the subspace of the symmetric matrix space.

Description

technical field [0001] The invention relates to a domain adaptive technology in the field of machine learning, in particular to a domain adaptive method on a Grassmannian manifold. Background technique [0002] In traditional related applications in the field of image recognition, it is usually assumed that the probability distributions of training data (source domain) and test data (target domain) are the same or similar. However, in practical applications, changes in factors such as illumination, background, and angles will cause large differences in the probability distributions of the source domain and the target domain, so the classifiers trained by the source domain data often cannot be generated in the target domain data. better effect. The domain adaptation task is to make the probability distribution of the source domain and the target domain data match as much as possible through related algorithms, so as to solve the problem of inconsistent probability distributi...

AI Technical Summary

Problems solved by technology

Therefore, the current domain adaptive method is usually suitable for Euclidean feature space data, while t

Images