Image retrieval algorithm based on distribution entropy gain loss function

Abstract

The invention discloses an image retrieval algorithm based on a distribution entropy gain loss function, and the algorithm employs a pre-training network for initialization, trains a network accordingto the demands of an image retrieval task, employs a self-designed distribution entropy gain loss function during the training of the network, and improves the accuracy of image retrieval. A distribution entropy gain loss function is combined with a comparison loss function and a relative entropy, so that the accuracy of image similarity measurement during network training is enhanced; the comparison loss function calculates the similarity between the features through the Euclidean distance, the relative entropy can be used for measuring the distribution difference between the feature vectors, and the relative entropy is supplemented to the comparison loss function to improve the similarity measurement of the feature vectors; a distribution entropy gain loss function is used for traininga network model, the network model more suitable for an image retrieval task is obtained by adjusting network parameters, and the trained network model obtains a better retrieval effect in an image retrieval experiment.

Description

technical field [0001] The invention belongs to the technical field of image retrieval and relates to an image retrieval algorithm for training a network through a distribution entropy gain loss function. Background technique [0002] With the vigorous development of Internet technology, social software is rich and diverse, and various forms of multimedia information are flooding our lives. How to quickly and accurately capture and effectively utilize multimedia information has become an important research topic, which has aroused widespread concern in the academic circles. Under this trend, image retrieval technology has been fully and comprehensively developed. [0003] In recent years, with the successful application of neural networks in image classification, researchers have paid more and more attention to the application of neural networks in the field of image retrieval. A large number of studies have shown that the features output by the convolutional layer of neura...

AI Technical Summary

Problems solved by technology

Although the pre-trained network has achieved amazing retrieval performance, it often does not have network parameters that match the image retrieval task, so image retrieval network fine-tuning has become a hot research topic

Images