ClsGAN: Selective Attribute Editing Model based on Classification Adversarial Network. (January 2021)

• Record Type: Journal Article
• Authors: Liu, Ying; Fan, Heng; Ni, Fuchuan; Xiang, Jinhai
• Is Part Of: Neural networks. Volume 133(2021)
• Page Start: 220
• Page End: 228
• Publication Date: 2021-01
• Subjects: GAN -- Attribute editing -- ClsGAN -- Upper convolution residual network (Tr-resnet) -- Attribute adversarial classifier (Atta-cls); Neural computers -- Periodicals; Neural networks (Computer science) -- Periodicals; Neural networks (Neurobiology) -- Periodicals; Nervous System -- Periodicals; Ordinateurs neuronaux -- Périodiques; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux neuronaux (Neurobiologie) -- Périodiques; Neural computers; Neural networks (Computer science); Neural networks (Neurobiology); Periodicals; 006.32
• DOI: 10.1016/j.neunet.2020.10.019
• Languages: English
• ISSNs: 0893-6080

Abstract

Abstract: Attribution editing has achieved remarkable progress in recent years owing to the encoder–decoder structure and generative adversarial network (GAN). However, it remains challenging to generate high-quality images with accurate attribute transformation. Attacking these problems, the work proposes a novel selective attribute editing model based on classification adversarial network (referred to as ClsGAN) that shows good balance between attribute transfer accuracy and photo-realistic images. Considering that the editing images are prone to be affected by original attribute due to skip-connection in encoder–decoder structure, an upper convolution residual network (referred to as Tr-resnet) is presented to selectively extract information from the source image and target label. In addition, to further improve the transfer accuracy of generated images, an attribute adversarial classifier (referred to as Atta-cls) is introduced to guide the generator from the perspective of attribute through learning the defects of attribute transfer images. Experimental results on CelebA demonstrate that our ClsGAN performs favorably against state-of-the-art approaches in image quality and transfer accuracy. Moreover, ablation studies are also designed to verify the great performance of Tr-resnet and Atta-cls. Highlights: ClsGAN is a attribute editing model based on classification adversarial network. An upper-conv residual net is to extract source image and target label information. Atta-cls is to guide generator from attribute by learning defects of transfer images. To keep label continuity, encoded attribute label is approximated to reference label.