典型文献
Unsupervised image-to-image translation by semantics consistency and self-attention
文献摘要：
Unsupervised image-to-image translation is a challenging task for computer vision.The goal of image translation is to learn a mapping between two domains,without corresponding image pairs.Many previous works only focused on image-level translation but ignored image features processing,which led to a certain semantics loss,such as the changes of the background of the generated image,partial transformation,and so on.In this work,we propose a method of image-to-image translation based on generative adversarial nets(GANs).We use autoencoder structure to extract image features in the generator and add semantic consistency loss on extracted features to maintain the semantic consistency of the generated image.Self-attention mechanism at the end of generator is used to obtain long-distance dependency in image.At the same time,as expanding the convolution receptive field,the quality of the generated image is enhanced.Quantitative experiment shows that our method significantly outperforms previous works.Especially on images with obvious foreground,our model shows an impressive improvement.
文献关键词：
中图分类号：
作者姓名：
ZHANG Zhibin;XUE Wanli;FU Guokai
作者机构：
The Key Laboratory of Computer Vision and System of Ministry of Education,Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology,Tianjin University of Technology,Tianjin 300384,China
文献出处：
引用格式：
[1]ZHANG Zhibin;XUE Wanli;FU Guokai-.Unsupervised image-to-image translation by semantics consistency and self-attention)[J].光电子快报（英文版）,2022(03):175-180
A类：
B类：
Unsupervised,translation,by,semantics,consistency,self,attention,challenging,task,computer,vision,goal,learn,mapping,between,two,domains,without,corresponding,pairs,Many,previous,works,only,focused,level,but,ignored,features,processing,which,led,certain,loss,such,changes,background,generated,partial,transformation,so,In,this,propose,method,generative,adversarial,nets,GANs,We,autoencoder,structure,generator,add,extracted,maintain,Self,mechanism,obtain,long,distance,dependency,At,same,expanding,convolution,receptive,field,quality,enhanced,Quantitative,experiment,shows,that,our,significantly,outperforms,Especially,images,obvious,foreground,model,impressive,improvement
AB值：
0.555447
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
