Content-based image retrieval method for unsupervised adversarial training

Abstract

The invention discloses a content-based image retrieval method for unsupervised adversarial training. The method comprises the following steps of: 1, carrying out network construction, wherein an unsupervised adversarial network framework consists of a generation model and a discrimination model, and both the generation model and the discrimination model are formed by three-layer full-connection networks; 2, carrying out data preprocessing; 3, carrying out network training: 3.1, initializing generation model and discrimination model parameters by using random weight values, 3.2, training the generation model, and 3.3, training the discrimination model; and 4, carrying out precision test. The content-based image retrieval method for unsupervised adversarial training is relatively good in robustness and relatively low in training data requirement, and does not need a large amount of label information.

Description

technical field [0001] The invention relates to multimedia big data processing and analysis in the field of computer vision, in particular to an unsupervised confrontational content-based image retrieval method, which belongs to the field of image retrieval. Background technique [0002] With the development of network sharing technology, more and more pictures on the network can be shared and received in real time. Content-based image retrieval technology occupies a very important part in the process of image processing. In recent years, with the rapid development of deep learning methods, the performance of content-based image retrieval technology has been greatly improved thanks to the accurate expression of image content by deep features. But this improvement is based on labeled training methods. When the training data label is not available, or the training data is small, the supervised training method based on the label cannot work well. Contents of the invention ...

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the disadvantages of poor robustness, high requirements for training data, and large amount of annotation information existing in the existing image retrieval technology, the present invention provides a method with better robustness, lower requirements for training data, and no need for a large amount of annotation information. Unsupervised Adversarial Training for Content-Based Image Retrieval

Images