Target domain detection network training method and device, equipment and storage medium

Abstract

The invention discloses a target domain detection network training method and device, equipment and a storage medium. The method comprises the following steps: constructing an encoding network, a source domain detection network and a target domain detection network based on source domain data and target domain data; updating the coding network, the source domain detection network and the target domain detection network according to the target function until the value of the target function meets a set condition, and in the updating process, enabling the source domain detection network and thetarget domain detection network to meet a maximum mean value difference constraint relationship; and taking the target domain detection network under the condition that the value of the target function meets a set condition as a trained target domain detection network. According to the technical scheme, the detection network used for identifying the target domain data is obtained through trainingaccording to the source domain data, the accuracy of identifying the target domain data is improved, and the data cost of the target domain detection network is reduced.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of image recognition, and in particular, to a training method, device, equipment and storage medium of an object domain detection network. Background technique [0002] With the rapid development of medical imaging equipment and artificial intelligence technology, medical data has grown on a large scale, and the analysis of artificial intelligence medical images based on deep learning has been gradually applied. A deep neural network can be trained based on a large amount of labeled data, and the application of this deep neural network can detect specific features, thereby identifying and classifying images, greatly reducing the workload of doctors, and improving diagnostic efficiency and accuracy. [0003] For deep neural networks, a large amount of labeled sample data is required to train the model, but in the medical field, it is difficult to obtain a large number of medical images, ...

AI Technical Summary

Problems solved by technology

[0003] For deep neural networks, a large amount of labeled sample data is required to train the model, but in the medical field, it is difficult to obtain a large number of medical images, and the cost of training data is high; Take the detection of pulmonary nodules on chest CT images as an example. There are obvious differences between chest CT images taken by different types of CT equipment. If these images with differences are directly mixed together to train the neural network, although the amount of data is sufficient, the The difference between images will lead to poor training effect and affect the detection accuracy, and it is difficult for the sample data to fully cover various data types. Once the CT image data of other types of CT equipment is replaced, the recognition accuracy is still low

Images