A Generative Adversarial Transfer Learning Method Based on Sketch Annotation Information

Abstract

The invention discloses a method for generating adversarial transfer learning based on sketch annotation information, obtaining an initial sketch image, and constructing a paired data set in the form of "source domain image-source domain image edge annotation map"; constructing an edge based on sketch annotation information Segment and train the deep network; select target domain samples based on matrix norm; construct and train a generation-adversarial transfer learning network based on sketch annotation information, which includes a deep generator network, a deep discriminator network, and an edge segmentation depth based on sketch annotation information Network and deep classifier network; input the target domain image, and obtain the classification result of the target domain image; the present invention utilizes the similarity of the source domain data and the target domain data structure, and through structural constraints, generates samples that conform to the distribution of the target domain to determine the label, In this way, the label is transmitted and the cross-domain classification is realized. The classification accuracy rate is improved, and the cross-domain classification task is realized.

Description

technical field [0001] The invention belongs to the technical field of image classification, and in particular relates to a generation confrontation transfer learning method based on sketch annotation information, which can be used for cross-domain image classification. Background technique [0002] Deep learning has achieved remarkable results in image classification. Under the traditional deep learning framework, the learning task is to learn a classification network on a given labeled training data set. The more parameters the model has, the more complex it is. However, with the advent of the era of big data, the cost of obtaining data is getting lower and lower, but the cost of calibrating data labels has not been reduced, making the deep learning network in processing this A blockage was encountered with some data. Deep transfer learning breaks the traditional framework, uses the data domains that have been marked, and transfers knowledge by looking for similarities be...

AI Technical Summary

Problems solved by technology

The problem with this type of method is that due to the abstraction of the feature space, it is actually impossible to judge whether the extracted features are domain-invariant features.

Images