Image Generation Method Based on Improved Generative Adversarial Network

Abstract

Background: The image generation model based on generative adversarial network (GAN) has achieved remarkable achievements. However, traditional GAN has the disadvantage of unstable training, which affects the quality of the generated image. Objective: This method is to solve the GAN image generation problems of poor image quality, single image category, and slow model convergence. Methods: An improved image generation method is proposed based on GAN. Firstly, the attention mechanism is introduced into the convolution layer of the generator and discriminator and a batch normalization layer is added after each convolution layer. Secondly, the ReLU and leaky ReLU are used as the active layer of the generator and discriminator, respectively. Thirdly, the transposed convolution is used in the generator while the small step convolution is used in the discriminator, respectively. Fourthly, a new discarding method is applied in the dropout layer. Results: The experiments were carried out on Caltech 101 dataset. The experimental results showed that the image quality generated by the proposed method is better than that generated by GAN with attention mechanism (AM-GAN) and GAN with stable training strategy (STS-GAN) and the stability was improved. Conclusion: The proposed method is effectiveness for image generation with high quality.