Domain self-adaption method based on triple and difference measurement

Abstract

The invention provides a domain self-adaption method based on a triple and difference measurement, which comprises the following steps of: randomly extracting samples from a target domain to form a target domain batch, and inputting a target domain batch to obtain sample features; inputting the sample features into a multi-classifier, and performing entropy minimization processing; inputting the sample features into a multi-binary classifier at the same time, and determining k critical samples and k pairs of similar classes according to the output; then, screening effective samples by utilizing triplet loss to construct a source domain batch, and training a multi-binary classifier and a multi-classifier through an extracted source domain batch sample; and finally, sending the target domain batch and the source domain batch into the domain adversarial network, and carrying out domain alignment operation. According to the method, a triple loss function is used, the margin between positive and negative sample pairs in the loss is reasonably designed, and domain alignment is carried out by using a domain adversarial network, so that sample distribution of a source domain and a target domain tends to be consistent, and samples, close to a classification boundary, of the target domain are indirectly far away from the boundary; therefore, the samples of which the target domains are close to the classification boundary can be correctly classified.

Description

technical field [0001] The invention relates to the technical field of machine learning, and mainly relates to a domain self-adaptation method based on triplets and difference metrics. Background technique [0002] With the continuous development of machine learning, especially the development of deep learning in its subfield, many machine learning tasks and computer vision applications have been greatly improved in terms of performance. However, this is also a prerequisite, we must There are enough labeled data to support us, and these labeled data can help us train an effective model to solve some practical problems. However, in actual scenarios, it is difficult to obtain a large amount of labeled data, which requires a lot of manpower and material resources. Therefore, how to find an effective method to solve the problem of missing labeled data is particularly critical. [0003] In the case of missing label data, the domain adaptive method is a reasonable solution. Doma...

AI Technical Summary

Problems solved by technology

However, these methods based on the idea of ​​domain confrontation are not able to solve the problem of the proximity of similar samples in the target domain. These similar samples are very close to the classification boundary of the two classes in the feature space, which makes it very difficult in the process of discrimination. It is easy to misjudge some target domain samples as similar categories

In the prior art, there is no public disclosure of how the domain adaptation method based on the domain confrontation idea can effectively solve the problem of discriminating similar samples in the target domain

Images