Transfer learning method for image classification, related device and storage medium

Abstract

The invention provides a transfer learning method for image classification, and relates to the technical field of artificial intelligence, and the method comprises the steps: mapping source domain image data and target domain image data to a manifold space, and obtaining a pseudo label of the target domain image data in the manifold space according to the source domain image data; aligning the source domain image data with the target domain image data with the pseudo label to obtain aligned source domain image data and aligned target domain image data; constructing a classifier by using the aligned source domain image data, and classifying the aligned target domain image data by using the constructed classifier to obtain a prediction label of the target domain image data; and classifying the target domain image data based on the prediction label to obtain a classification result. According to the embodiment of the invention, the method facilitates the improvement of the transfer learning effect, and improves the image classification accuracy. In addition, the invention also relates to a blockchain technology, and the constructed classifier can be stored in a blockchain node.

Description

technical field [0001] The present application relates to the technical field of machine learning, and in particular to a transfer learning method for image classification, related devices and storage media. Background technique [0002] With the development of artificial intelligence and machine learning, transfer learning is widely used in various classification problems such as images and texts. Traditional transfer learning algorithms usually use a large amount of source domain data to train a classifier for classifying target domain data on the assumption that the source domain and target domain data obey the same distribution. However, this assumption is difficult to be satisfied in actual scenarios. Based on this, a method to reduce the difference in data distribution between the two domains is also proposed in the prior art. It is considered that there is a common manifold between the source domain and the target domain, and the source domain and the target domain ar...

AI Technical Summary

Problems solved by technology

However, in practical applications, there is no corresponding point pair between the source domain and the target domain to achieve the alignment of the two domain manifolds. This method is not representative, and the migration effect is still not ideal.

Images