Image-text cross-modal hash retrieval method based on large-batch training

Abstract

The invention relates to an image-text cross-modal hash retrieval method based on large-batch training, and belongs to the field of cross-modal retrieval, and is used for solving the problems that theexisting deep learning-based cross-modal hash retrieval method, particularly a triple-based deep cross-modal hash method, is long in small-batch training time, limited in obtained sample number and not good enough in gradient, so that the retrieval performance is influenced. The method comprises the following steps: preprocessing an image and text data; carrying out hash code mapping; establishing a target loss function L; inputting the triple data training model in a large-batch manner; and performing cross-modal hash retrieval by using the trained model. According to the scheme provided bythe invention, the triple data is input in a large-batch manner for training, so that the time of each round of training is shortened; because more training samples exist when the parameters are updated each time, a better gradient can be obtained, orthogonal regularization is used for the weight, the gradient can be kept during gradient transmission, model training is more stable, and the retrieval accuracy is improved.

Description

technical field [0001] The invention belongs to the field of cross-modal retrieval, and relates to a graphic-text cross-modal hash retrieval method based on mass training. Background technique [0002] With the rapid development of the Internet and multimedia technology, a large amount of multimedia data in different modalities has been generated, such as images, texts, videos, etc. Data of different modalities can be used to describe the same thing, and displaying information from multiple perspectives can help users gain a comprehensive understanding of the thing. With the rapid growth of multimedia data of different modalities, cross-modal retrieval has become a research hotspot. The key to cross-modal retrieval is to model the relationship between multimedia data of different modalities. The main difficulty is that there is a heterogeneity gap in multimedia data of different modalities, and direct comparison cannot be made. [0003] The cross-modal hashing method can e...

AI Technical Summary

Problems solved by technology

[0007] In view of this, the purpose of the present invention is to provide a method for cross-modal hash retrieval of images and texts based on large-scale training, which is used to solve the existing cross-modal hash retrieval method based on deep learning, especially based on triplets The small batch training time of the deep cross-modal hashing method is long, the number of samples obtained is limited, and the gradient is not good enough to affect the retrieval performance

Images