Unsupervised domain adaptive method combining deep attention features and conditional adversarial

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to an unsupervised domain adaptive method combining deep attention features and conditional adversarial. The methodcomprises the following steps: dividing a to-be-processed image data set into a source domain and a target domain; designing a network capable of migrating attention and conditional confrontation; preprocessing the image source domain and the target domain before the image source domain and the target domain are inputa network capable of migrating attention and conditional adversarial; importingthe preprocessed source domain and the preprocessed target domain into the designed network in batches in sequence, obtaining weighted feature maps through a migratable attention network, inputting the weighted feature maps into a conditional adversarial network for training, and finally performing probability operation through a full connection layer; respectively calculating the image classification accuracy of the source domain and the target domain; and finally, directly applying the network which is trained on the source domain and can migrate attention and conditional adversarial to thetarget domain to perform image classification through iteration and back propagation training. According to the method, the generalization ability of the unsupervised domain adaptive network is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence and relates to an unsupervised domain self-adaptive method combining deep attention features and conditional confrontation. Background technique [0002] Although deep networks have greatly improved the performance of various machine learning problems and applications with their rich feature representation capabilities, their training process relies heavily on a large number of labeled training samples based on supervised learning. In the real world, manual annotation of large amounts of such data for various application scenarios is often prohibitively expensive. Domain adaptation is a well-studied strategy that improves target datasets by transferring knowledge from labeled source datasets without using target labels. However, this good learning paradigm faces the problem of domain shift, which makes it a great obstacle to directly apply the model learned on the source domain to...

AI Technical Summary

Problems solved by technology

If we force matching non-transferable features, it may lead to negative transfer

Images