基于特征增强的人脸属性转换

魏子涵; 王慧; 王晶; 高岚; 张伟功

Chinese

您当前的位置：

首页 >

文章列表页 >

基于特征增强的人脸属性转换

更新时间：2026-09-04

- 基于特征增强的人脸属性转换
- Face attribute transfer based on feature enhancement
- 微电子学与计算机 2020年37卷第10期页码：38-41
- 作者机构：
  
  1. 首都师范大学机构北京成像理论与技术高精尖创新中心,北京,100048
  2. 西安电子科技大学电子工程学院,陕西,西安,710126
  3. 首都师范大学信息工程学院,北京,100048
  4. 电子系统可靠性技术北京市重点实验室机构,北京,100048
- 作者简介：
- 基金信息：
  
  国家自然科学基金 61772350北京市高水平教师队伍建设计划 CIT%amp;TCD201704082北京市科技新星计划项目 Z181100006218093北京未来芯片技术高精尖创新中心科研基金资助项目 KYJJ2018008
- DOI：
  中图分类号：
- 纸质出版：2020
- 稿件说明：
移动端阅览
魏子涵, 王慧, 王晶, 高岚, 张伟功. 基于特征增强的人脸属性转换[J]. 微电子学与计算机, 2020, 37(10): 38-41, 47.

WEI Zi-han, WANG Hui, WANG Jing, et al. Face attribute transfer based on feature enhancement[J]. 2020, 37(10): 38-41.
魏子涵, 王慧, 王晶, 高岚, 张伟功. 基于特征增强的人脸属性转换[J]. 微电子学与计算机, 2020, 37(10): 38-41, 47. DOI：

WEI Zi-han, WANG Hui, WANG Jing, et al. Face attribute transfer based on feature enhancement[J]. 2020, 37(10): 38-41. DOI：

摘要

采用生成对抗网络及其扩展模型可以实现人脸属性转换，但生成图像存在分辨率低及特征损失的问题.本文基于GeneGAN网络，提出一种基于特征增强的人脸属性转换算法，在生成网络中增加网络深度，建立高低维特征耦合通道，通过对特定属性深度特征提取比较，优化生成图像的身份及属性特征.在CelebA数据集上的实验表明，本文算法得到的高分辨率图像不仅在保留图像身份信息上有较好的改善，同时在视觉效果和客观指标上都有较大的提高.

Abstract

The current facial attribute transformation based on generative adversarial networks (GAN) and GAN-based method has problems of low resolution and feature loss of the generated image. Based on the GeneGAN network

this paper proposes a face attribute conversion algorithm based on feature enhancement. By increasing the network depth in the generation network

establishing a high- and low-dimensional feature coupling channel

and extracting and comparing specific attribute depth features to optimize the identity and features of the generated image. Experiment based on CelebA dataset shows that the high-resolution images generated by the proposed algorithm have a better improvement in maintaining image identity information

and have a greater improvement in visual effects and objective indicators.

关键词

Keywords

references

HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets [J]. Neural Computation, 2006, 18(7): 1527-1554. DOI: 1527

ZHOU S, XIAO T, YANG Y, et al. GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data[C]. 28th British Machine Vision Conference (BMVC2017). London, UK, 2017: 111.1-111.13.

RATLIFF L J, BURDEN S A, SASTRY S S. Characterization and computation of local Nash equilibria in continuous games[C]. 51st IEEE Annual Allerton Conference on Communication, Control and Computing. Monticello, IL, USA, 2013: 917-924.

JOHNSON J, ALAHI A, LI F. Perceptual Losses for Real-Time Style Transfer and Super-Resolution[C]. 14th European Conference on Computer Vision. Amsterdam, NETHERLANDS, 2016: 694-711.

RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]. 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Munich, GERMANY, 2015: 234-241.

GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative Adversarial Nets[C]. 28th Conference on Neural Information Processing Systems (NIPS2014). Montreal, CANADA, 2014: 2672-2680.

LIU Z, LUO P, WANG X, et al. Deep Learning Face Attributes in the Wild[C]. IEEE International Conference on Computer Vision (ICCV2015). Santiago, CHILE, 2015: 3730-3738.

TRAN L, YIN X, LIU X. Disentangled Representation Learning GAN for Pose-Invariant Face Recognition[C]. 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2017). Honolulu, HI, USA, 2017: 1283-1292.

SCHROFF F, KALENICHENKO D, PHILBIN J. FaceNet: A Unified Embedding for Face Recognition and Clustering[C]. 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2015). Boston, MA, USA, 2015: 815-823.

REN S, HE K, GIRSHICK R, et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis % Machine Intelligence, 2017, 39(6):1137-1149. DOI: 1137

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于注意力-生成式对抗网络的异常行为检测

基于改进RT-DETR的航拍小目标检测算法

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

面向处理器分支预测单元的Spectre攻击轻量化防御方法

注意力机制与改进密集卷积引导的信息隐藏模型