Multi-semantic deep supervision cross-mode hash retrieval method

Abstract

The invention particularly relates to a multi-semantic deep supervision cross-mode hash retrieval method. According to the multi-semantic deep supervision cross-mode hash retrieval method, the methodcomprises the following steps: utilizing a deep neural network, combining supervision semantic information of training data, and learning hash mapping models of multiple modes respectively; sending image query data of a given specific mode into a neural network of a corresponding mode, converting the image mode data into a hash code through hash mapping learned by a deep network, then calculatingthe distance between the hash code and a hash code of another mode in a database, and finally returning data most similar to query. According to the multi-semantic deep supervision cross-mode hash retrieval method, various high-level semantic information is fully utilized, the similarity relation between data modes and label semantic information in the modes are kept, high-quality hash codes can be obtained, hash learning and classification tasks are combined in the same stream for learning, the learning efficiency is improved, and then information retrieval between data of different modes isachieved.

Description

technical field [0001] The invention relates to the technical field of information retrieval, in particular to a multi-semantic deep-supervised cross-modal hash retrieval method. Background technique [0002] With the development of Internet technology, the forms of media data presented on the network are becoming more and more diverse, and multimedia applications are becoming more and more common. Data may have various modes such as images, texts, videos, and audios. Users' search needs are no longer limited to a single modality, so cross-modal hash retrieval technology has attracted more and more researchers' attention, and has also been widely used in the field of information retrieval. [0003] Hash retrieval technology has the advantages of fast retrieval speed and low storage consumption, mainly because hash technology can map high-dimensional original data into low-dimensional Hamming space. The original data in Hamming space can be represented by multiple 0 / 1 hash c...

AI Technical Summary

Problems solved by technology

However, the heterogeneity between different modalities increases the difficulty of cross-modal retrieval, leading to the fact that the existing excellent single-modal hash retrieval technology cannot be directly applied to cross-modal retrieval.

Images