Semi-Supervised FaceGAN for Face-Age Progression and Regression with Synthesized Paired Images
Abstract
:1. Introduction
- We proposed a novel framework for age progression and regression including two GAN models. By using an additional GAN, we can train the model with a semi-supervised approach with synthesized paired images, which avoids the limitations of real datasets.
- We introduced a new way of training that separates the aging features and identity features so that we can better train our model. With our proposed method, we can use a Unet-based model as a generator, which can overcome the bottleneck limitation of auto-encoder. This helps our model to produce more detailed images.
2. Related Works
3. Method
3.1. Baseline Method
3.2. Proposed Model
3.3. The Conditional StyleGAN
3.4. The FaceGAN
4. Experiments
4.1. Dataset
4.2. Implementation Details
4.3. The Qualitative Results
4.4. The Quantitative Results
5. Conclusions
Author Contributions
Funding
Conflicts of Interest
Appendix A. The cStyleGAN Architecture
Layer | Kernel Size; Padding | Output Shape |
---|---|---|
StyledConvBlock with ConstantInput | 3 × 3; 1 | 512 × 8 × 8 |
UpSample | - | 512 × 16 × 16 |
StyledConvBlock | 3 × 3; 1 | 512 × 16 × 16 |
UpSample | - | 512 × 32 × 32 |
StyledConvBlock | 3 × 3; 1 | 512 × 32 × 32 |
UpSample | - | 512 × 64 × 64 |
StyledConvBlock | 3 × 3; 1 | 512 × 64 × 64 |
UpSample | - | 512 × 128 × 128 |
StyledConvBlock | 3 × 3; 1 | 512 × 128 × 128 |
Layer | Kernel Size; Padding | Activation | Output Shape |
---|---|---|---|
Input Image | - | - | 9 × 128 × 128 |
Conv (from_rgb) | 1 × 1; 1 | - | 128 × 128 × 128 |
Conv | 3 × 3; 1 | LeakyReLU | 128 × 128 × 128 |
Conv | 3 × 3; 1 | LeakyReLU | 128 × 128 × 128 |
DownSample | - | 128 × 64 × 64 | |
Conv | 3 × 3; 1 | LeakyReLU | 256 × 64 × 64 |
Conv | 3 × 3; 1 | LeakyReLU | 256 × 64 × 64 |
DownSample | - | - | 256 × 32 × 32 |
Conv | 3 × 3; 1 | LeakyReLU | 512 × 32 × 32 |
Conv | 3 × 3; 1 | LeakyReLU | 512 × 32 × 32 |
DownSample | - | - | 512 × 16 × 16 |
Conv | 3 × 3; 1 | LeakyReLU | 512 × 16 × 16 |
Conv | 3 × 3; 1 | LeakyReLU | 512 × 16 × 16 |
DownSample | - | - | 512 × 8 × 8 |
Minibatch stddev | - | - | 513 × 8 × 8 |
Conv | 3 × 3; 1 | LeakyReLU | 512 × 8 × 8 |
Conv | 8 × 8; 0 | LeakyReLU | 512 × 1 × 1 |
Fully-Connected | - | linear | 1 × 1 × 1 |
References
- Fu, Y.; Guo, G.; Huang, T.S. Age Synthesis and Estimation via Faces: A Survey. IEEE Trans. Pattern Anal. Mach. Intell. 2010, 32, 1955–1976. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Z.; Song, Y.; Qi, H. Age Progression/Regression by Conditional Adversarial Autoencoder. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017. [Google Scholar]
- Shu, X.; Tang, J.; Lai, H.; Liu, L.; Yan, S. Personalized Age Progression with Aging Dictionary. In Proceedings of the 2015 IEEE International Conference on Computer Vision (ICCV), ICCV ’15, Santiago, Chile, 7–13 December 2015; IEEE Computer Society: Washington, DC, USA, 2015; pp. 3970–3978. [Google Scholar] [CrossRef] [Green Version]
- Wang, W.; Cui, Z.; Yan, Y.; Feng, J.; Yan, S.; Shu, X.; Sebe, N. Recurrent Face Aging. In Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016; pp. 2378–2386. [Google Scholar] [CrossRef]
- Rothe, R.; Timofte, R.; Gool, L.V. Deep expectation of real and apparent age from a single image without facial landmarks. Int. J. Comput. Vis. 2016. [Google Scholar] [CrossRef] [Green Version]
- Rothe, R.; Timofte, R.; Gool, L.V. DEX: Deep EXpectation of apparent age from a single image. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW), Santiago, Chile, 7–13 December 2015. [Google Scholar]
- Agustsson, E.; Timofte, R.; Escalera, S.; Baró, X.; Guyon, I.; Rothe, R. Apparent and real age estimation in still images with deep residual regressors on APPA-REAL database. In Proceedings of the 12th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG 2017), Washington, DC, USA, 30 May–3 June 2017. [Google Scholar]
- Antipov, G.; Baccouche, M.; Dugelay, J. Face aging with conditional generative adversarial networks. In Proceedings of the 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, 17–20 September 2017; pp. 2089–2093. [Google Scholar] [CrossRef] [Green Version]
- Yang, H.; Huang, D.; Wang, Y.; Jain, A.K. Learning Face Age Progression: A Pyramid Architecture of GANs. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 31–39. [Google Scholar] [CrossRef] [Green Version]
- Wang, Z.; Tang, X.; Luo, W.; Gao, S. Face Aging with Identity-Preserved Conditional Generative Adversarial Networks. In Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA, 18–23 June 2018. [Google Scholar]
- Liu, S.; Sun, Y.; Zhu, D.; Bao, R.; Wang, W.; Shu, X.; Yan, S. Face Aging with Contextual Generative Adversarial Nets. In Proceedings of the ACM Multimedia, Mountain View, CA, USA, 23–27 October 2017. [Google Scholar]
- Karras, T.; Aila, T.; Laine, S.; Lehtinen, J. Progressive Growing of GANs for Improved Quality, Stability, and Variation. In Proceedings of the 6th International Conference on Learning Representations, Vancouver, BC, Canada, 30 April–3 May 2018. [Google Scholar]
- Karras, T.; Laine, S.; Aila, T. A Style-Based Generator Architecture for Generative Adversarial Networks. In Proceedings of the 2018 Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018. [Google Scholar]
- Suo, J.; Zhu, S.; Shan, S.; Chen, X. A Compositional and Dynamic Model for Face Aging. IEEE Trans. Pattern Anal. Mach. Intell. 2010, 32, 385–401. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Shen, C.T.; Huang, F.; Lu, W.H.; Shih, S.W.; Liao, H.Y. 3D Age Progression Prediction in Children’s Faces with a Small Exemplar-Image Set. J. Inf. Sci. Eng. 2014, 30, 1131–1148. [Google Scholar]
- Rowland, D.A.; Perrett, D.I. Manipulating facial appearance through shape and color. IEEE Comput. Graph. Appl. 1995, 15, 70–76. [Google Scholar] [CrossRef] [Green Version]
- Kemelmacher-Shlizerman, I.; Suwajanakorn, S.; Seitz, S.M. Illumination-Aware Age Progression. In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, 23–28 June 2014; pp. 3334–3341. [Google Scholar] [CrossRef] [Green Version]
- Goodfellow, I.J.; Pouget-Abadie, J.; Mirza, M.; Xu, B.; Warde-Farley, D.; Ozair, S.; Courville, A.; Bengio, Y. Generative Adversarial Nets. In Proceedings of the 27th International Conference on Neural Information Processing Systems, Mandi, India, 16–19 December 2014; MIT Press: Cambridge, MA, USA, 2014; Volume 2, pp. 2672–2680. [Google Scholar]
- Radford, A.; Metz, L.; Chintala, S. Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks. In Proceedings of the International Conference on Learning Representations, San Juan, Puerto Rico, 2–4 May 2016. [Google Scholar]
- Brock, A.; Donahue, J.; Simonyan, K. Large Scale GAN Training for High Fidelity Natural Image Synthesis. In Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA, 6–9 May 2019. [Google Scholar]
- Mirza, M.; Osindero, S. Conditional Generative Adversarial Nets. arXiv 2014, arXiv:1411.1784. [Google Scholar]
- Odena, A.; Olah, C.; Shlens, J. Conditional Image Synthesis with Auxiliary Classifier GANs. In Proceedings of the 34th International Conference on Machine Learning, ICML’17, Sydney, Australia, 6–11 August 2017; Volume 70, pp. 2642–2651. [Google Scholar]
- Isola, P.; Zhu, J.Y.; Zhou, T.; Efros, A.A. Image-to-Image Translation with Conditional Adversarial Networks. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 5967–5976. [Google Scholar]
- Zhu, J.Y.; Park, T.; Isola, P.; Efros, A.A. Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. In Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22–29 October 2017; pp. 2242–2251. [Google Scholar]
- Chen, X.; Xu, C.; Yang, X.; Song, L.; Tao, D. Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer. IEEE Trans. Image Process. 2019, 28, 546–560. [Google Scholar] [CrossRef] [PubMed]
- Ledig, C.; Theis, L.; Huszár, F.; Caballero, J.; Cunningham, A.; Acosta, A.; Aitken, A.; Tejani, A.; Totz, J.; Wang, Z.; et al. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 105–114. [Google Scholar] [CrossRef] [Green Version]
- Nazeri, K.; Ng, E.; Ebrahimi, M. Image Colorization Using Generative Adversarial Networks. In International Conference on Articulated Motion and Deformable Objects; Springer: Berlin/Heidelberg, Germany, 2018; pp. 85–94. [Google Scholar]
- Yang, H.; Huang, D.; Wang, Y.; Jain, A.K. Learning Continuous Face Age Progression: A Pyramid of GANs. IEEE Trans. Pattern Anal. Mach. Intell. 2019. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Liu, Y.; Li, Q.; Sun, Z. Attribute Enhanced Face Aging with Wavelet-based Generative Adversarial Networks. arXiv 2018, arXiv:1809.06647. [Google Scholar]
- Wang, C.; Liu, H.; Pei, S.; Liu, K.; Liu, T. Face Aging on Realistic Photos by Generative Adversarial Networks. In Proceedings of the 2019 IEEE International Symposium on Circuits and Systems (ISCAS), Sapporo, Hokkaido, Japan, 26–29 May 2019; pp. 1–5. [Google Scholar] [CrossRef]
- Duong, C.N.; Luu, K.; Quach, K.G.; Nguyen, N.; Patterson, E.; Bui, T.D.; Le, N. Automatic Face Aging in Videos via Deep Reinforcement Learning. In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 16–20 June 2019; pp. 10005–10014. [Google Scholar] [CrossRef] [Green Version]
- Genovese, A.; Piuri, V.; Scotti, F. Towards Explainable Face Aging with Generative Adversarial Networks. In Proceedings of the 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 22–29 September 2019; pp. 3806–3810. [Google Scholar] [CrossRef] [Green Version]
- Li, P.; Hu, Y.; Li, Q.; He, R.; Sun, Z. Global and Local Consistent Age Generative Adversarial Networks. In Proceedings of the 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 20–24 August 2018; pp. 1073–1078. [Google Scholar] [CrossRef] [Green Version]
- Palsson, S.; Agustsson, E.; Timofte, R.; Van Gool, L. Generative Adversarial Style Transfer Networks for Face Aging. In Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA, 18–22 June 2018; pp. 2165–2168. [Google Scholar] [CrossRef]
- Baldi, P. Autoencoders, Unsupervised Learning and Deep Architectures. Proc. ICML Unsupervised Transf. Learn. 2011, 27, 37–50. [Google Scholar]
- Goodfellow, I.J. NIPS 2016 Tutorial: Generative Adversarial Networks. arXiv 2017, arXiv:1701.00160. [Google Scholar]
- Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015; Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F., Eds.; Springer International Publishing: Cham, Switzerland, 2015; pp. 234–241. [Google Scholar]
- Huang, X.; Belongie, S. Arbitrary Style Transfer in Real-Time with Adaptive Instance Normalization. In Proceedings of the 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22–29 October 2017; pp. 1510–1519. [Google Scholar] [CrossRef] [Green Version]
- Panis, G.; Lanitis, A.; Tsapatsoulis, N.; Cootes, T.F. Overview of research on facial ageing using the FG-NET ageing database. IET Biom. 2016, 5, 37–46. [Google Scholar] [CrossRef]
- Kingma, D.P.; Ba, J. Adam: A Method for Stochastic Optimization. In Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, 7–9 May 2015. [Google Scholar]
- Zhang, K.; Zhang, Z.; Li, Z.; Qiao, Y. Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks. IEEE Signal Process. Lett. 2016, 23, 1499–1503. [Google Scholar] [CrossRef] [Green Version]
- Cao, Q.; Shen, L.; Xie, W.; Parkhi, O.M.; Zisserman, A. VGGFace2: A Dataset for Recognising Faces across Pose and Age. In Proceedings of the 2018 13th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2018), Xi’an, China, 15–19 May 2018; pp. 67–74. [Google Scholar]
- Huang, X.; Liu, M.Y.; Belongie, S.; Kautz, J. Multimodal Unsupervised Image-to-image Translation. In Proceedings of the 15th European Conference on Computer Vision,(ECCV 2018), Munich, Germany, 8–14 September 2018. [Google Scholar]
- Lee, S.; Ha, J.; Kim, G. Harmonizing Maximum Likelihood with GANs for Multimodal Conditional Generation. In Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA, 6–9 May 2019. [Google Scholar]
- Gulrajani, I.; Ahmed, F.; Arjovsky, M.; Dumoulin, V.; Courville, A. Improved Training of Wasserstein GANs. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, Long Beach, CA, USA, 4–9 December 2017; Curran Associates Inc.: Red Hook, NY, USA, 2017; pp. 5769–5779. [Google Scholar]
IPCGANs | CAAE | SS-FaceGAN | |
---|---|---|---|
0–10 years old | 0.33 | 0.34 | 0.32 |
11–20 | 0.35 | 0.37 | 0.32 |
21–30 | 0.32 | 0.37 | 0.29 |
31–40 | 0.33 | 0.37 | 0.28 |
41–50 | 0.36 | 0.36 | 0.28 |
51+ | 0.34 | 0.35 | 0.29 |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Pham, Q.T.M.; Yang, J.; Shin, J. Semi-Supervised FaceGAN for Face-Age Progression and Regression with Synthesized Paired Images. Electronics 2020, 9, 603. https://doi.org/10.3390/electronics9040603
Pham QTM, Yang J, Shin J. Semi-Supervised FaceGAN for Face-Age Progression and Regression with Synthesized Paired Images. Electronics. 2020; 9(4):603. https://doi.org/10.3390/electronics9040603
Chicago/Turabian StylePham, Quang T. M., Janghoon Yang, and Jitae Shin. 2020. "Semi-Supervised FaceGAN for Face-Age Progression and Regression with Synthesized Paired Images" Electronics 9, no. 4: 603. https://doi.org/10.3390/electronics9040603
APA StylePham, Q. T. M., Yang, J., & Shin, J. (2020). Semi-Supervised FaceGAN for Face-Age Progression and Regression with Synthesized Paired Images. Electronics, 9(4), 603. https://doi.org/10.3390/electronics9040603