Unsupervised field adaptation method and system based on adversarial learning and medium

Abstract

The invention provides an unsupervised field adaptation method and system based on adversarial learning and a medium, and the method comprises the steps: a feature extraction step: employing a featureextraction network to extract the features of images in a source field and a target field, and obtaining the image features of the source field and the image features of the target field; a categoryprediction step: predicting the probability that the image belongs to each category according to the obtained image feature of the source field and the image feature of the target field, and obtaininga category prediction probability; and a field discrimination step: predicting the probability that the image feature comes from the source field and the target field through a field discrimination network according to the obtained image feature of the source field and the image feature of the target field, and obtaining a field prediction probability. According to the method, the characteristicsthat the image extraction fields in the source field and the target field are invariable and have relatively high discrimination capability can be realized, so that the unsupervised field adaptationis realized.

Description

technical field [0001] The present invention relates to methods in the field of computer vision and image processing, in particular to an unsupervised domain adaptation method, system and medium based on adversarial learning. Background technique [0002] The deep neural network model has received more and more attention because of its excellent performance in many fields. Training a deep neural network model often requires a large amount of labeled data. However, collecting a large-scale labeled dataset for each new task is extremely time-consuming and labor-intensive. Fortunately, we can find data for related tasks in other domains, and using these auxiliary data may help reduce the current task's dependence on labeling a new data set. However, due to differences in data collection methods, etc., the distribution of data in two different fields is often different. Due to the existence of "domain shift", the model trained on one domain is directly tested on another domai...

AI Technical Summary

Problems solved by technology

However, this patent document does not use the method of confrontational learning, and does not consider the importance of feature discrimination to domain adaptation

Images