Double-attention generative adversarial network based on channel enhancement and image generation method

Abstract

The invention relates to a double-attention generative adversarial network based on channel enhancement and an image generation method. The network comprises a generator and a discriminator. The generator comprises a convolution block I and a double-attention mechanism module; the discriminator comprises a convolution block II and a double-attention mechanism module; compression activation operation layers used for obtaining channel attention through compression activation operation are arranged in the convolution block I and the convolution block II; the double-attention mechanism module comprises a position attention unit and a channel attention unit which are parallel to each other; the position attention unit establishes inter-position relevance based on a self-attention mechanism to obtain position attention features, and the channel attention unit establishes inter-feature channel dependence based on a channel attention mechanism to obtain channel attention features; and the double attention mechanism module fuses the position attention features and the channel attention features. According to the invention, the generation performance of the generative adversarial network canbe improved, the generated data distribution is closer to the original data distribution, and the generated image quality is better.

Description

technical field [0001] The invention relates to the technical field of image generation, in particular to a channel enhancement-based dual-attention generation confrontation network and an image generation method. Background technique [0002] Generative Adversarial Network (GAN) technology is mainly used in the direction of image generation. The Generative Adversarial Network model consists of a generator and a discriminator. The generator can generate images according to the input noise vector or category label. The discriminator is used to distinguish the authenticity of the image. The generator and discriminator confrontation training enables the generator to learn the real data distribution. , the final generator can approximate fake images of real images. Generative confrontation network technology is widely used in image enhancement, infrared image generation, medical image generation, image super-resolution reconstruction and other directions. [0003] At present, ...

AI Technical Summary

Problems solved by technology

[0004] Although the current GAN generation ability is already very strong, it is still difficult to generate images of complex scenes with a wide range of correlations using only the noise vector z and the conditional label y in the case of little prior knowledge.

Existing GAN models are difficult to generate images with complex structural distributions

Although the self-attention mechanism enables the generative confrontation network to generate images with a wide range of correlations, there are still some defects in the target object structure in the generated images.

At the same time, it is difficult to generate images containing multiple target object scenes, and the quality of generated images needs to be improved

Images