Huang, Zhitong 
ORCID: https://orcid.org/0000-0001-6982-4815
(2020)
Identity-Preserved Face Beauty Transformation with Conditional Generative Adversarial Networks.
Masters thesis, Concordia University.
Preview |
Text (application/pdf)
11MBHuang_MCompSc_F2020.pdf - Accepted Version Available under License Spectrum Terms of Access. |
Abstract
Identity-preserved face beauty transformation aims to change the beauty scale of a face image while preserving the identity of the original face. In our framework of conditional Generative Adversarial Networks (cGANs), the synthesized face produced by the generator would have the same beauty scale indicated by the input condition. Unlike the discrete class labels used in most cGANs, the condition of target beauty scale in our framework is given by a continuous real-valued beauty score in the range [1 to 5], which makes the work challenging. To tackle the problem, we implement a new triple structure, in which the conditional discriminator is divided into a normal discriminator and a separate face beauty predictor. We also develop another new structure called Conditioned Instance Normalization to replace the original concatenation used in cGANs, which makes the combination of the input image and condition more effective. Furthermore, Self -Consistency Loss is introduced as a new parameter to improve the stability of training and quality of the generated image. In the end, the objectives of beauty transformation and identity preservation are evaluated by the pretrained face beauty predictor and state-of the-art face recognition network. The result shows that certain facial features could be synthesized by the generator according to the target beauty scale, while preserving the original identity.
| Divisions: | Concordia University > Gina Cody School of Engineering and Computer Science > Computer Science and Software Engineering Concordia University > Research Units > Centre for Pattern Recognition and Machine Intelligence |
|---|---|
| Item Type: | Thesis (Masters) |
| Authors: | Huang, Zhitong |
| Institution: | Concordia University |
| Degree Name: | M. Comp. Sc. |
| Program: | Computer Science |
| Date: | 1 August 2020 |
| Thesis Supervisor(s): | Suen, Ching Yee |
| Keywords: | Face beauty transformation, Identity-preserved, conditional generative adversarial networks. |
| ID Code: | 987073 |
| Deposited By: | zhitong huang |
| Deposited On: | 30 Jun 2021 15:04 |
| Last Modified: | 01 Aug 2022 00:00 |
References:
[1] C. LI et al., “Triple generative adversarial nets,” in Advances in Neural Information Processing Systems 30, 2017, pp. 4088–4098.[2] J. Xu et al., A new humanlike facial attractiveness predictor with cascaded fine-tuning deep learning model, 2015. arXiv: 1511.02465 [cs.CV].
[3] L. Lin et al., “R2-resnext: A resnext-based regression model with relative ranking for facial beauty prediction,” in Proc. 24th International Conference on Pattern Recognition (ICPR), Aug. 2018, pp. 85–90.
[4] S. Shi et al., “Improving facial attractiveness prediction via coattention learning,” in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp. 4045–4049.
[5] L. Xu et al., “Hierarchical multi-task network for race, gender and facial attractiveness recognition,” in Proc. IEEE International Conference on Image Processing (ICIP), 2019, pp. 3861–3865.
[6] I. Goodfellow et al., “Generative adversarial nets,” in Advances in Neural Information Processing Systems 27, 2014, pp. 2672-2680.
[7] L. A. Gatys et al., “Image style transfer using convolutional neural networks,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2016, pp. 2414–2423.
[8] D. Ulyanov et al., “Improved texture networks: Maximizing quality and diversity in feed-forward stylization and texture synthesis,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4105–4113.
[9] X. Huang and S. Belongie, “Arbitrary style transfer in real-time with adaptive instance normalization,” in Proc. IEEE International Conference on Computer Vision (ICCV), Oct. 2017, pp. 1501–1510.
[10] P. Isola et al., “Image-to-image translation with conditional adversarial networks,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 5967–5976.
[11] Y. Choi et al., “Stargan: Unified generative adversarial networks for multi-domain image-to-image translation,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2018, pp. 8789–8797.
[12] J.-Y. Zhu et al., “Unpaired image-to-image translation using cycle-consistent adversarial networks,” in Proc. IEEE International Conference on Computer Vision (ICCV), Oct. 2017, pp. 2223–2232.
[13] M. Mirza and S. Osindero, Conditional generative adversarial nets, 2014. arXiv: 1411. 1784 [cs.LG].
[14] Z. Wang et al., “Face aging with identity-preserved conditional generative adversarial networks,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jun. 2018, pp. 7939–7947.
[15] G. Antipov et al., “Face aging with conditional generative adversarial networks,” in Proc. IEEE International Conference on Image Processing (ICIP), 2017, pp. 2089–2093.
[16] V. Dumoulin et al., A learned representation for artistic style, 2016. arXiv: 1610. 07629 [cs.CV].
[17] N. Diamant et al., “Beholder-gan: Generation and beautification of facial images with conditioning on their beauty level,” in Proc. IEEE International Conference on Image Processing (ICIP), 2019, pp. 739–743.
[18] T. Karras et al., Progressive growing of gans for improved quality, stability, and variation, 2017. arXiv: 1710.10196 [cs.NE].
[19] L. Liang et al., “Scut-fbp5500: A diverse benchmark dataset for multi-paradigm facial beauty prediction,” in Proc. 24th International Conference on Pattern Recognition (ICPR), 2018, pp. 1598–1603.
[20] T. Li et al., “Beautygan: Instance-level facial makeup transfer with deep generative adversarial network,” in Proc. ACM international conference on Multimedia, Oct. 2018, pp. 645–653.
[21] G. E. Hinton and R. R. Salakhutdinov, “Reducing the dimensionality of data with neural networks,” science, vol. 313, no. 5786, pp. 504–507, 2006.
[22] X. Mao et al., “Least squares generative adversarial networks,” in Proc. IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2813–2821.
[23] K. He et al., “Deep residual learning for image recognition,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778.
[24] J. Deng et al., “Imagenet: A large-scale hierarchical image database,” in Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2009, pp. 248–255.
[25] S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” in Proc. International Conference on Machine Learning (ICML), vol. 37, Jul. 2015, pp. 448–456.
[26] O. M. Parkhi et al., “Deep face recognition,” in Proceedings of the British Machine Vision Conference (BMVC), Sep. 2015, pp. 41.1–41.12.
[27] T. Salimans and D. P. Kingma, “Weight normalization: A simple parameterization to accelerate training of deep neural networks,” in Advances in Neural Information Processing Systems 29, 2016, pp. 901–909.
[28] M. Arjovsky et al., “Wasserstein generative adversarial networks,” in Proceedings of the 34th International Conference on Machine Learning, vol. 70, Aug. 2017, pp. 214–223.
Repository Staff Only: item control page
Download Statistics
Download Statistics