Lightweight Network for Multi-Attribute Style Image Generation Based on StarGAN
The generation countermeasure network has been widely used in image-to-image translation tasks,in which multi-attribute transformation has been studied and applied increasingly.However,the existing network architecture has many parameters and complex models,requiring high computing and storage costs;the traditional network compression technology mainly focuses on visual recognition tasks,and rarely implements the compression of generated tasks.Therefore,in this article we propose a method stuStarGAN to train the student network with fewer parameters by learning the low-level and high-level features of StarGAN.In our proposed method,first,we distill the generator with knowledge distillation,and design the student discriminator so that the teacher discriminator distills the student discriminator;then in the student net-work design,skip-connection is used to provide cross module feature fusion;second,the content loss function is added to keep the consistency of the content information between the generated image and the original image;finally,depth separable convolution is used to further reduce the number of parameters and improve the quality of image generation.The experimen-tal results on benchmark datasets showed that the model could generate multi-attribute style images with fewer parameters without reducing the generation quality,making it easy to transplant to various application scenarios.
GANknowledge distillationskip-connectiondepth separable convolutioncontent loss
万方数据
维普
