Domain adaptation method based on Fredholm learning and adversarial learning

Abstract

The invention discloses a domain adaptation method based on Fredholm learning and adversarial learning, and the method comprises the steps: feature extraction: extracting features of source domain data Xs and target domain data Xt through the same feature extractor; domain identification: after the extracted features are obtained, identifying which domain the features belong to; wherein the domainidentification is divided into two stages: (1) obtaining Fredholm characteristics; (2) identifying by a domain identifier; and sample classification: using two classifiers, a classification module receiving the features extracted by the feature extractor, inputting the features into a full connection layer for calculation, and outputting classification results from a source domain classifier Cs and a target domain classifier Ct after softmax. The domain adaptation method based on Fredholm learning and adversarial learning provided by the invention has the beneficial effect that a better classification effect can be achieved in image classification.

Description

Technical field [0001] The invention relates to the field of computer technology, in particular to a domain adaptation method based on Fredholm learning and confrontation learning. Background technique [0002] Domain adaptation is a method in deep transfer learning. Generally speaking, the effectiveness of deep learning methods relies on a large amount of labeled training data. However, it is very difficult to collect enough training data for each task domain. Through domain adaptation, you can have sufficient training data. The model trained on the source domain of the data is migrated to the relevant but different target domain, which solves the problem that the target domain lacks training data and is difficult to use other depth methods. [0003] Earlier domain adaptation methods often use some measurement methods, such as Maximum Mean Difference (MMD) to measure the difference between the source domain and the target domain, and then minimize the difference to make the model...

AI Technical Summary

Problems solved by technology

However, these methods ignore the influence of noise factors in domain adaptation. In practical applications, the extracted features will contain noise information in the sample, and these wrong information will mislead the judgment of the model and reduce the performance of the model.

Images