Mode collapse resistant robust image generation method based on novel conditional generative adversarial network

Abstract

The invention discloses a mode collapse resistant robust image generation method based on a novel conditional generative adversarial network. Compared with a method in the related art, the technologydisclosed by the invention has the advantages that the adaptability is strong, the robustness is good, only the category of a required image is required to be specified in the using phase, not manualintervention is required in the process, the training phase is short in consumed time, the training process is stable, and the balance between the diversity and the authenticity of generated images issufficiently maintained. The main innovation of the mode collapse resistant robust image generation method lies in that a mode collapse problem and a training failure problem in the training processof other conditional generative methods are solved. Meanwhile, parameters are respectively optimized for a classifier and a discriminator, thereby avoiding problems of instable training and mode collapse of the methods of the same category. In addition, the invention further introduces a construction strategy for weight sharing, so that the training speed is greatly improved and the storage overhead is reduced under the premise of not damaging the original performance. The mode collapse resistant robust image generation method is applied to a diversified image data generation task of low-costlarge-scale specified labels.

Description

technical field [0001] The invention belongs to the fields of image modeling, computer vision, and image generation, and relates to an anti-mode collapse robust image generation method based on a novel conditional confrontation generation network, which is mainly used for large-scale image generation of designated category labels. Background technique [0002] With the rapid development of artificial intelligence and deep learning, machine learning methods based on large-scale data have been more and more widely recognized and applied. However, no matter how excellent an intelligent analysis algorithm is, it must also take high-quality input information as the basic premise, and low-quality input information will inevitably directly affect the overall analysis effect of the algorithm. However, labeled datasets require a lot of manual labor for tedious and detailed calibration. In order to ensure data quality, an additional label verification and verification process is requi...

AI Technical Summary

Problems solved by technology

[0004] In order to constrain the label categories of generated images, certain conditional constraints need to be added in the process of generator generation. In previous related research, some work on conditional generative models, but t

Images