一级黄色片免费播放|中国黄色视频播放片|日本三级a|可以直接考播黄片影视免费一级毛片

高級搜索

留言板

尊敬的讀者、作者、審稿人, 關(guān)于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復(fù)。謝謝您的支持!

姓名
郵箱
手機(jī)號碼
標(biāo)題
留言內(nèi)容
驗證碼

基于改進(jìn)循環(huán)生成式對抗網(wǎng)絡(luò)的圖像風(fēng)格遷移

張驚雷 厚雅偉

張驚雷, 厚雅偉. 基于改進(jìn)循環(huán)生成式對抗網(wǎng)絡(luò)的圖像風(fēng)格遷移[J]. 電子與信息學(xué)報, 2020, 42(5): 1216-1222. doi: 10.11999/JEIT190407
引用本文: 張驚雷, 厚雅偉. 基于改進(jìn)循環(huán)生成式對抗網(wǎng)絡(luò)的圖像風(fēng)格遷移[J]. 電子與信息學(xué)報, 2020, 42(5): 1216-1222. doi: 10.11999/JEIT190407
Jinglei ZHANG, Yawei HOU. Image-to-image Translation Based on Improved Cycle-consistent Generative Adversarial Network[J]. Journal of Electronics & Information Technology, 2020, 42(5): 1216-1222. doi: 10.11999/JEIT190407
Citation: Jinglei ZHANG, Yawei HOU. Image-to-image Translation Based on Improved Cycle-consistent Generative Adversarial Network[J]. Journal of Electronics & Information Technology, 2020, 42(5): 1216-1222. doi: 10.11999/JEIT190407

基于改進(jìn)循環(huán)生成式對抗網(wǎng)絡(luò)的圖像風(fēng)格遷移

doi: 10.11999/JEIT190407
詳細(xì)信息
    作者簡介:

    張驚雷:男,1969,教授,博士,研究方向為模式識別、圖像處理等

    厚雅偉:男,1995,碩士生,研究方向為圖像處理、目標(biāo)檢測等

    通訊作者:

    張驚雷 zhangjinglei@tjut.edu.cn

  • 中圖分類號: TN911.73; TP317

Image-to-image Translation Based on Improved Cycle-consistent Generative Adversarial Network

  • 摘要:

    圖像間的風(fēng)格遷移是一類將圖片在不同領(lǐng)域進(jìn)行轉(zhuǎn)換的方法。隨著生成式對抗網(wǎng)絡(luò)在深度學(xué)習(xí)中的快速發(fā)展,其在圖像風(fēng)格遷移領(lǐng)域中的應(yīng)用被日益關(guān)注。但經(jīng)典算法存在配對訓(xùn)練數(shù)據(jù)較難獲取,生成圖片效果差的缺點。該文提出一種改進(jìn)循環(huán)生成式對抗網(wǎng)絡(luò)(CycleGAN++),取消了環(huán)形網(wǎng)絡(luò),并在圖像生成階段將目標(biāo)域與源域的先驗信息與相應(yīng)圖片進(jìn)行縱深級聯(lián);優(yōu)化了損失函數(shù),采用分類損失代替循環(huán)一致?lián)p失,實現(xiàn)了不依賴訓(xùn)練數(shù)據(jù)映射的圖像風(fēng)格遷移。采用CelebA和Cityscapes數(shù)據(jù)集進(jìn)行實驗評測,結(jié)果表明在亞馬遜勞務(wù)平臺感知研究(AMT perceptual studies)與全卷積網(wǎng)絡(luò)得分(FCN score)兩個經(jīng)典測試指標(biāo)中,該文算法比CycleGAN, IcGAN, CoGAN, DIAT等經(jīng)典算法取得了更高的精度。

  • 圖  1  CycleGAN中單向GAN網(wǎng)絡(luò)結(jié)構(gòu)圖

    圖  2  CycleGAN++的網(wǎng)絡(luò)結(jié)構(gòu)

    圖  3  CycleGAN++的生成網(wǎng)絡(luò)

    圖  4  CycleGAN++的判別網(wǎng)絡(luò)

    圖  5  CycleGAN與CycleGAN++的訓(xùn)練過程對比

    圖  6  CycleGAN++在人物性別轉(zhuǎn)換領(lǐng)域下的可視化結(jié)果

    圖  7  CycleGAN++與原算法在CelebA測試集下的對比

    圖  8  CycleGAN++與原算法在Cityscapes測試集下的對比

    表  1  CycleGAN+與原算法的AMT測試結(jié)果對比(%)

    方法男性→女性女性→男性照片→標(biāo)簽標(biāo)簽→照片
    CycleGAN24.6±2.321.1±1.826.8±2.823.2±3.4
    CycleGAN+29.5±3.229.2±4.127.8±2.228.2±2.4
    下載: 導(dǎo)出CSV

    表  2  CycleGAN+與原算法的FCN得分結(jié)果對比

    方法每像素精度每類精度IoU分類
    CycleGAN0.520.170.11
    CycleGAN+0.600.210.16
    下載: 導(dǎo)出CSV

    表  3  CycleGAN++與CycleGAN+的AMT感知研究結(jié)果對比(%)

    方法男性→女性女性→男性照片→標(biāo)簽標(biāo)簽→照片
    CycleGAN+29.5±3.229.2±4.127.8±2.228.2±2.4
    本文CycleGAN++31.4±3.832.6±4.730.1±2.630.9±2.7
    下載: 導(dǎo)出CSV

    表  4  CycleGAN++與CycleGAN+的FCN得分結(jié)果對比

    方法每像素精度每類精度IoU分類
    CycleGAN+0.600.210.16
    本文CycleGAN++0.690.270.23
    下載: 導(dǎo)出CSV

    表  5  各算法的AMT感知研究結(jié)果對比(%)

    方法男性→女性女性→男性照片→標(biāo)簽標(biāo)簽→照片
    CycleGAN[12]24.6±2.321.1±1.826.8±2.823.2±3.4
    IcGAN[22]23.2±2.522.4±2.922.8±2.619.8±1.9
    CoGAN[10]6.8±1.15.1±0.90.6±0.50.9±0.5
    DIAT[21]31.1±3.930.2±3.628.4±2.927.2±2.5
    本文CycleGAN++31.4±3.832.6±4.730.1±2.630.9±2.7
    下載: 導(dǎo)出CSV

    表  6  各算法的FCN得分結(jié)果對比

    方法每像素精度每類精度IoU分類
    CycleGAN[12]0.520.170.11
    IcGAN[22]0.430.110.07
    CoGAN[10]0.400.100.06
    DIAT[21]0.680.240.21
    本文CycleGAN++0.690.270.23
    下載: 導(dǎo)出CSV
  • HERTZMANN A, JACOBS C E, OLIVER N, et al. Image analogies[C]. The 28th Annual Conference on Computer Graphics and Interactive Techniques, New York, USA, 2001: 327–340. doi: 10.1145/383259.383295.
    GOODFELLOW I J, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]. The 27th International Conference on Neural Information Processing Systems, Montreal, Canada, 2014: 2672–2680.
    RADFORD A, METZ L, and CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[EB/OL]. https://arxiv.org/abs/1511.06434, 2015.
    ARJOVSKY M, CHINTALA S, and BOTTOU L. Wasserstein GAN[EB/OL]. https://arxiv.org/abs/1701.07875, 2017.
    GULRAJANI I, AHMED F, ARJOVSKY M, et al. Improved training of wasserstein GANs[C]. The 31st International Conference on Neural Information Processing Systems, Red Hook, USA, 2017: 5769–5779.
    ISOLA P, ZHU Junyan, ZHOU Tinghui, et al. Image-to-image translation with conditional adversarial networks[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 5967–5976. doi: 10.1109/CVPR.2017.632.
    MIRZA M and OSINDERO S. Conditional generative adversarial nets[EB/OL]. https://arxiv.org/abs/1411.1784, 2014.
    ROSALES R, ACHAN K, and FREY B. Unsupervised image translation[C]. The 9th IEEE International Conference on Computer Vision, Nice, France, 2003: 472–478. doi: 10.1109/ICCV.2003.1238384.
    LIU Mingyu, BREUEL T, KAUTZ J, et al. Unsupervised image-to-image translation networks[C]. The 31st Conference on Neural Information Processing Systems, Long Beach, USA, 2017: 700–708.
    LIU Mingyu and TUZEL O. Coupled generative adversarial networks[C]. The 30th Conference on Neural Information Processing Systems, Barcelona, Spain, 2016: 469–477.
    KINGMA D P and WELLING M. Auto-encoding variational bayes[EB/OL]. https://arxiv.org/abs/1312.6114, 2013.
    ZHU Junyan, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]. 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 2242–2251. doi: 10.1109/ICCV.2017.244.
    KIM T, CHA M, KIM H, et al. Learning to discover cross-domain relations with generative adversarial networks[C]. The 34th International Conference on Machine Learning, Sydney, Australia, 2017: 1857–1865.
    YI Zili, ZHANG Hao, TAN Ping, et al. DualGAN: Unsupervised dual learning for image-to-image translation[C]. 2017 IEEE International Conference on Computer Vision, Venice, Italy, 2017: 2868–2876. doi: 10.1109/ICCV.2017.310.
    BOUSMALIS K, SILBERMAN N, DOHAN D, et al. Unsupervised pixel-level domain adaptation with generative adversarial networks[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 95–104. doi: 10.1109/CVPR.2017.18.
    SHRIVASTAVA A, PFISTER T, TUZEL O, et al. Learning from simulated and unsupervised images through adversarial training[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, 2017: 2242–2251. doi: 10.1109/CVPR.2017.241.
    TAIGMAN Y, POLYAK A, and Wolf L. Unsupervised cross-domain image generation[EB/OL]. https://arxiv.org/abs/1611.02200, 2016.
    LI Chuan and WAND M. Precomputed real-time texture synthesis with markovian generative adversarial networks[C]. The 14th European Conference on Computer Vision, Amsterdam, The Netherlands, 2016: 702–716. doi: 10.1007/978-3-319-46487-9_43.
    LIU Ziwei, LUO Ping, WANG Xiaogang, et al. Deep learning face attributes in the wild[C]. 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 3730–3738. doi: 10.1109/ICCV.2015.425.
    KINGMA D P and BA J. Adam: A method for stochastic optimization[EB/OL]. https://arxiv.org/abs/1412.6980, 2014.
    LI Mu, ZUO Wangmeng, and ZHANG D. Deep identity-aware transfer of facial attributes[EB/OL]. https://arxiv.org/abs/1610.05586, 2016.
    PERARNAU G, VAN DE WEIJER J, RADUCANU B, et al. Invertible conditional GANs for image editing[EB/OL]. https://arxiv.org/abs/1611.06355, 2016.
  • 加載中
圖(8) / 表(6)
計量
  • 文章訪問數(shù):  5044
  • HTML全文瀏覽量:  2404
  • PDF下載量:  315
  • 被引次數(shù): 0
出版歷程
  • 收稿日期:  2019-06-05
  • 修回日期:  2019-12-23
  • 網(wǎng)絡(luò)出版日期:  2019-12-31
  • 刊出日期:  2020-06-04

目錄

    /

    返回文章
    返回