Cross-domain adaptive semantic segmentation method and device based on data disturbance

Abstract

The invention provides a cross-domain adaptive semantic segmentation method and device based on data perturbation; the method comprises the steps: obtaining to-be-processed data and semantic segmentation features after data perturbation is added; determining a loss function based on the to-be-processed data and the semantic segmentation features; acquiring a cross-domain adaptive semantic segmentation model through an error back propagation algorithm training model based on the loss function. According to the invention, disturbance is randomly added to a large amount of label-free data in a target domain, and it is guaranteed that the image subjected to disturbance processing can keep semantic consistency; therefore, the problem of field inconsistency between a source domain and a target domain is solved from two perspectives of data disturbance and a cross-domain prototype classifier; in addition, a targeted design is made for a small amount of supervision problems with higher practical application value in practical application, and excellent segmentation performance is obtained under an adversarial-based learning framework; thereby migrating the knowledge of the existing labeled sample into the new data model.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a method and device for cross-domain self-adaptive semantic segmentation based on data disturbance. Background technique [0002] As a kind of transfer learning, domain adaptation is an important and challenging task in the field of machine learning, and it has a wide range of applications in image recognition, object detection, and image semantic segmentation. In the era of big data, massive amounts of data are generated every day, but it is difficult to obtain labeled data that can be used for machine learning, because the labeling of these data requires time-consuming fine labeling, such as semantic segmentation labeling at the pixel level, and some require The annotators have sufficient knowledge and experience in the main business, such as the annotation of medical images, and some are difficult to annotate due to the huge amount of data. [0003] Therefore, how to p...

AI Technical Summary

Problems solved by technology

In the era of big data, massive amounts of data are generated every day, but it is difficult to obtain labeled data that can be used for machine learning, because the labeling of these data requires time-consuming fine labeling, such as semantic segmentation labeling at the pixel level, and some require The annotators have sufficient knowledge and experience in the main business, such as the annotation of medical images, and some are difficult to annotate due to the huge amount of data

Images