ClsGAN: Selective Attribute Editing Model Based On Classification Adversarial Network

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 in generating 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.

References in corpus (15)

• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Autoencoding beyond pixels using a learned similarity metric
• Invertible Conditional GANs for image editing
• Deep Identity-aware Transfer of Facial Attributes
• DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images
• GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data
• RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributes
• UGAN: Untraceable GAN for Multi-Domain Face Translation
• Attribute Guided Unpaired Image-to-Image Translation with Semi-supervised Learning
• Fully-Featured Attribute Transfer
• Image-to-Image Translation with Multi-Path Consistency Regularization