Unsupervised cross-modal hash retrieval method and system based on virtual label regression

Abstract

The invention provides an unsupervised cross-modal hash retrieval method and system based on virtual label regression, and the method comprises the steps: feature representation and hash function learning are integrated into a unified depth frame, and a shared hash code is learned through the cooperative matrix decomposition of multi-modal depth features, so as to guarantee that a plurality of modes share the same semanteme; on the basis, the concept of a virtual label is introduced, the virtual label is learned through non-negative spectrum analysis, and meanwhile, the learned virtual labelis returned to the hash code, so that the semantic consistency between the hash code and the virtual label is ensured; in the framework, collaborative matrix decomposition of the depth features and learning and regression of the virtual tags are beneficial to learning of depth feature representation and hash functions, and improved depth feature representation and hash models are beneficial to collaborative matrix decomposition and learning and regression of the virtual tags, and the collaborative matrix decomposition and the virtual tags promote each other; and meanwhile, through a new discrete optimization strategy, the deep hash function and the hash code are directly updated, the quantization error of a relaxation strategy in an existing method is effectively reduced, and the cross-modal retrieval performance is improved.

Description

technical field [0001] The present disclosure relates to the technical field of cross-modal retrieval, in particular to an unsupervised cross-modal hash retrieval method and system based on virtual tag regression. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art. [0003] With the rapid development of the mobile Internet, multimodal data on the Internet is showing an explosive growth trend. In the field of information retrieval, the rapid growth of multimodal data has brought about a huge demand for cross-modal retrieval applications. Cross-modal retrieval is to model the relationship between different modalities to achieve retrieval between modalities. The modalities of the query data and the data to be retrieved do not have to be the same, such as retrieving images by text and retrieving text by images. Exploring new cross-modal retrieval modes ...

AI Technical Summary

Problems solved by technology

[0005] The inventors of the present disclosure found in the research that although a variety of unsupervised cross-modal hash retrieval methods have been proposed, there are still the following problems: (1) most of the existing methods are based on shallow models, simply using linear or non-linear Linear mapping is used for hash learning, resulting in limited expression ability of the learned hash code; (2) Without the guidance of semantic labels, the semantic information contained in the learned hash code is limited, and the lack of semantic information will directly affect the retrieval accuracy ; (3) Most of them use the two-step optimization strategy of "relaxation + quantization" to solve the hash code, and there is a large quantization error in the solution process

Images