In image generation tasks,generative adversarial networks usually prefer to learn low-level patterns,such as tex-tures of images,but ignore high-level patterns,such as their shapes.To solve this problem,this paper proposes a residual attention multi-channel generative adversarial network.Firstly,the residual connection is used to make information transmission more effi-cient and the model training becomes more stable.Secondly,the self-attention mechanism is introduced to improve the long-range dependence of the generated images and enhance the modeling capacity of the model on shapes.Thirdly,the model's FID score is further improved by using the concatenation of RGB and HS channels of an image as the input of the discriminator,where the HS channels hides the luminance details while highlighting the object contours in the figure.The experimental results show that the mod-el is able to generate images with better visual effects on datasets with complex geometric structures.
维普
万方数据