计算机科学 ›› 2022, Vol. 49 ›› Issue (2): 31-39.doi: 10.11896/jsjkx.210600012
石达, 芦天亮, 杜彦辉, 张建岭, 暴雨轩
SHI Da, LU Tian-liang, DU Yan-hui, ZHANG Jian-ling, BAO Yu-xuan
摘要: 深度伪造可以将人的声音、面部及身体动作拼接,从而合成虚假内容,用于转换性别、改变年龄等。基于生成对抗式图像翻译网络的人脸性别伪造图像存在容易改变无关图像域、人脸细节不够丰富等问题。针对这些问题,文中提出基于改进CycleGAN的人脸性别伪造图像生成模型。首先,优化生成器结构,利用注意力机制与自适应残差块提取更丰富的人脸特征;然后,借鉴相对损失的思想对损失函数进行改进,提高判别器的判别能力。最后,提出基于年龄约束的模型训练策略,减小了年龄变化对生成图像的影响。在CelebA和IMDB-WIKI数据集上进行实验,实验结果表明,与原始CycleGAN方法和UGATIT方法相比,所提方法能够生成更加真实的人脸性别伪造图像,伪造男性和伪造女性的平均内容准确率分别为82.65%和78.83%,FID平均得分分别为32.14和34.50。
中图分类号:
[1]BAO Y X,LU T L,DU Y H.Overview of Deepfake Video Detection Technology[J].Computer Science,2020,47(9):283-292. [2]Deepfakes[OL].https://github.com/deepfakes/faceswap. [3]FaceSwap[OL].https://github.com/MarekKowalski/FaceSwap/. [4]THIES J,ZOLLHOFER M,STAMMINGER M,et al.Face2-face:Real-time face capture and reenactment of rgb videos[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016:2387-2395. [5]Faceswap-GAN[OL].https://github.com/shaoanlu/faceswap-GAN. [6]ISOLA P,ZHU J Y,ZHOU T,et al.Image-to-image translation with conditional adversarial networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1125-1134. [7]ZHU J Y,PARK T,ISOLA P,et al.Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//Proceedings of the IEEE International Conference on Vomputer vision.2017:2223-2232. [8]KIM J,KIM M,KANG H,et al.U-GAT-IT:unsupervised ge-nerative attentional networks with adaptive layer-instance normalization for image-to-image translation[J].arXiv:1907.10830,2019. [9]WANG Z,TANG X,LUO W,et al.Face aging with identity-preserved conditional generative adversarial networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7939-7947. [10]ARJOVSKY M,CHINTALA S,BOTTOU L.Wasserstein ge-nerative adversarial networks[C]//International Conference on Machine Learning.PMLR,2017:214-223. [11]MAO X,LI Q,XIE H,et al.Least squares generative adversarial networks[C]//Proceedings of the IEEE International Confe-rence on Computer Vision.2017:2794-2802. [12]GULRAJANI I,AHMES F,ARJOVSKY M,et al.Improvedtraining of wasserstein gans[J].arXiv:1704.00028,2017. [13]UPCHURCH P,GARDNER J,PLEISS G,et al.Deep feature interpolation for image content changes[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:7064-7073. [14]PERARNAU G,VAN DE WEIJER J,et al.Invertible conditio-nal gans for image editing[J].arXiv:1611.06355,2016. [15]WANG S M,LI S F.Multi-domain image conversion methodbased on feature vector transformation GAN[J].Journal of Yunnan University(Natural Sciences Edition),2020,42(6):1080-1090. [16]LIU M Y,BREUEL T,KAUTZ J.Unsupervised image-to-image translation networks[J].arXiv:1703.00848,2017. [17]HUANG X,LIU M Y,BELONGIE S,et al.Multimodal unsupervised image-to-image translation[C]//Proceedings of the European Conference on Computer Vision (ECCV).2018:172-189. [18]PARK D Y,LEE K H.Arbitrary style transfer with style-attentional networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:5880-5888. [19]XIAO T,HONG J,MA J.Elegant:Exchanging latent encodings with gan for transferring multiple face attributes[C]//Procee-dings of the European Conference on Computer Vision (ECCV).2018:168-184. [20]CHO W,CHOI S,PARK D K,et al.Image-to-image translation via group-wise deep whitening-and-coloring transformation[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2019:10639-10647. [21]MA Z,LI J,WANG N,et al.Semantic-related image style trans-fer with dual-consistency loss[J].Neurocomputing,2020,406:135-149. [22]CHOI Y,CHOI M,KIM M,et al.Stargan:Unified generativeadversarial networks for multi-domain image-to-image translation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:8789-8797. [23]SANAKOYEU A,KOTOVENKO D,LANG S,et al.A style-aware content loss for real-time hd style transfer[C]//Procee-dings of the European Conference on Computer Vision (ECCV).2018:698-714. [24]WU H M,LIU Q R,WANG Y H.Face image translation based on generative adversarial networks[J].Journal of Tianjin University:Science and Technology,2019,52(3):306-314. [25]PENG Y F,WANG K X,MEI J Y,et al.Image style migration based on cycle generative adversarial networks[J].Computer Engineering & Science,2020,42(4):699-706. [26]BAO J,CHEN D,WEN F,et al.CVAE-GAN:fine-grainedimage generation through asymmetric training[C]//Proceedings of the IEEE International Conference on Computer Vision.2017:2745-2754. [27]WOO S,PARK J,LEE J Y,et al.Cbam:Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV).2018:3-19. [28]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2018:7132-7141. [29]ULYANOV D,VEDALDI A,LEMPITSKY V.Instance nor-malization:The missing ingredient for fast stylization[J].arXiv:1607.08022,2016. [30]BA J L,KIROS J R,HINTON G E.Layer normalization[J].arXiv:1607.06450,2016. [31]JOLICOEUR-MARTINEAU A.The relativistic discriminator:a key element missing from standard GAN[J].arXiv:1807.00734,2018. [32]KINGMA D P,BA J.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014. |
[1] | 张佳, 董守斌. 基于评论方面级用户偏好迁移的跨领域推荐算法 Cross-domain Recommendation Based on Review Aspect-level User Preference Transfer 计算机科学, 2022, 49(9): 41-47. https://doi.org/10.11896/jsjkx.220200131 |
[2] | 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204 |
[3] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
[4] | 汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108 |
[5] | 王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099 |
[6] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
[7] | 姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046 |
[8] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
[9] | 胡艳羽, 赵龙, 董祥军. 一种用于癌症分类的两阶段深度特征选择提取算法 Two-stage Deep Feature Selection Extraction Algorithm for Cancer Classification 计算机科学, 2022, 49(7): 73-78. https://doi.org/10.11896/jsjkx.210500092 |
[10] | 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮. 基于DNGAN的磁共振图像超分辨率重建算法 Super-resolution Reconstruction of MRI Based on DNGAN 计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105 |
[11] | 程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157 |
[12] | 侯钰涛, 阿布都克力木·阿布力孜, 哈里旦木·阿布都克里木. 中文预训练模型研究进展 Advances in Chinese Pre-training Models 计算机科学, 2022, 49(7): 148-163. https://doi.org/10.11896/jsjkx.211200018 |
[13] | 周慧, 施皓晨, 屠要峰, 黄圣君. 基于主动采样的深度鲁棒神经网络学习 Robust Deep Neural Network Learning Based on Active Sampling 计算机科学, 2022, 49(7): 164-169. https://doi.org/10.11896/jsjkx.210600044 |
[14] | 苏丹宁, 曹桂涛, 王燕楠, 王宏, 任赫. 小样本雷达辐射源识别的深度学习方法综述 Survey of Deep Learning for Radar Emitter Identification Based on Small Sample 计算机科学, 2022, 49(7): 226-235. https://doi.org/10.11896/jsjkx.210600138 |
[15] | 刘伟业, 鲁慧民, 李玉鹏, 马宁. 指静脉识别技术研究综述 Survey on Finger Vein Recognition Research 计算机科学, 2022, 49(6A): 1-11. https://doi.org/10.11896/jsjkx.210400056 |
|