Abstract
Current age datasets lie in a long-tailed distribution, which brings difficulties to describe the aging mechanism for the imbalance ages. To alleviate it, we design a novel facial age prior to guide the aging mechanism modeling. To explore the age effects on facial images, we propose a Disentangled Adversarial Autoencoder (DAAE) to disentangle the facial images into three independent factors: age, identity and extraneous information. To avoid the “wash away” of age and identity information in face aging process, we propose a hierarchical conditional generator by passing the disentangled identity and age embeddings to the high-level and low-level layers with class-conditional BatchNorm. Finally, a disentangled adversarial learning mechanism is introduced to boost the image quality for face aging. In this way, when manipulating the age distribution, DAAE can achieve face aging with arbitrary ages. Further, given an input face image, the mean value of the learned age posterior distribution can be treated as an age estimator. These indicate that DAAE can efficiently and accurately estimate the age distribution in a disentangling manner. DAAE is the first attempt to achieve facial age analysis tasks, including face aging with arbitrary ages, exemplar-based face aging and age estimation, in a universal framework. The qualitative and quantitative experiments demonstrate the superiority of DAAE on five popular datasets, including CACD2000, Morph, UTKFace, FG-NET and AgeDB.
P. Li, H. Huang and R. He—Equal contribution.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Face++ research toolkit. megvii inc. http://www.faceplusplus.com ([Online])
Burgess, C.P., et al.: Understanding disentangling in beta-VAE. arXiv preprint arXiv:1804.03599 (2018)
Chen, B.C., Chen, C.S., Hsu, W.H.: Face recognition and retrieval using cross-age reference coding with cross-age celebrity dataset. IEEE Trans. Multimed. 17(6), 804–815 (2015)
Chen, S., Zhang, C., Dong, M., Le, J., Rao, M.: Using ranking-CNN for age estimation. In: CVPR (2017)
De Vries, H., Strub, F., Mary, J., Larochelle, H., Pietquin, O., Courville, A.C.: Modulating early visual processing by language. In: NeurIPS (2017)
Gao, B.B., Zhou, H.Y., Wu, J., Geng, X.: Age estimation using expectation of label distribution learning. In: IJCAI (2018)
Gao, B.B., Zhou, H.Y., Wu, J., Geng, X.: Age estimation using expectation of label distribution learning. In: IJCAI (2018)
Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)
Gulrajani, I., et al.: Pixelvae: a latent variable model for natural images. arXiv preprint arXiv:1611.05013 (2016)
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)
Hou, X., Shen, L., Sun, K., Qiu, G.: Deep feature consistent variational autoencoder. In: WACV (2017)
Huang, H., He, R., Sun, Z., Tan, T., et al.: Introvae: introspective variational autoencoders for photographic image synthesis. In: NeurIPS (2018)
Kemelmacher-Shlizerman, I., Suwajanakorn, S., Seitz, S.M.: Illumination-aware age progression. In: CVPR (2014)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: ICLR (2014)
Lanitis, A., Taylor, C.J., Cootes, T.F.: Toward automatic simulation of aging effects on face images. IEEE Trans. Pattern Anal. Mach. Intell. 24(4), 442–455 (2002)
Li, P., Hu, Y., He, R., Sun, Z.: Global and local consistent wavelet-domain age synthesis. IEEE Trans. Inf. Forensics Secur. 14, 2943–2957 (2018)
Li, P., Hu, Y., Li, Q., He, R., Sun, Z.: Global and local consistent age generative adversarial networks. In: ICPR (2018)
Li, P., Hu, Y., Wu, X., He, R., Sun, Z.: Deep label refinement for age estimation. Pattern Recogn. 100, 107–178 (2020)
Liu, Y., Li, Q., Sun, Z.: Attribute-aware face aging with wavelet-based generative adversarial networks. In: CVPR (2019)
Moschoglou, S., Papaioannou, A., Sagonas, C., Deng, J., Kotsia, I., Zafeiriou, S.: AgeDB: the first manually collected, in-the-wild age database. In: CVPRW (2017)
Moschoglou, S., Ververas, E., Panagakis, Y., Nicolaou, M.A., Zafeiriou, S.: Multi-attribute robust component analysis for facial uv maps. IEEE J. Sel. Top. Signal Process. 12(6), 1324–1337 (2018)
Niu, Z., Zhou, M., Wang, L., Gao, X., Hua, G.: Ordinal regression with multiple output CNN for age estimation. In: CVPR (2016)
Pan, H., Han, H., Shan, S., Chen, X.: Mean-variance loss for deep age estimation from a face. In: CVPR (2018)
Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: ICML (2014)
Ricanek, K., Tesafaye, T.: Morph: a longitudinal image database of normal adult age-progression. In: FGR (2006)
Rothe, R., Timofte, R., Van Gool, L.: Deep expectation of real and apparent age from a single image without facial landmarks. Int. J. Comput. Vis. 126(2–4), 144–157 (2018)
Sagonas, C., Ververas, E., Panagakis, Y., Zafeiriou, S.: Recovering joint and individual components in facial data. IEEE Trans. Pattern Anal. Mach. Intell. 40(11), 2668–2681 (2017)
Semeniuta, S., Severyn, A., Barth, E.: A hybrid convolutional variational autoencoder for text generation. arXiv preprint arXiv:1702.02390 (2017)
Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. In: NeurIPS (2015)
Wang, W., et al.: Recurrent face aging. In: CVPR (2016)
Wang, Z., Tang, X., Luo, W., Gao, S.: Face aging with identity-preserved conditional generative adversarial networks. In: CVPR (2018)
Wu, X., He, R., Sun, Z., Tan, T.: A light CNN for deep face representation with noisy labels. IEEE Trans. Inf. Forensics Secur. 13(11), 2884–2896 (2018)
Wu, X., Huang, H., Patel, V.M., He, R., Sun, Z.: Disentangled variational representation for heterogeneous face recognition. In: AAAI (2019)
Yang, H., Huang, D., Wang, Y., Jain, A.K.: Learning face age progression: a pyramid architecture of GANs. In: CVPR (2018)
Yang, T.Y., Huang, Y.H., Lin, Y.Y., Hsiu, P.C., Chuang, Y.Y.: SSR-NET: a compact soft stagewise regression network for age estimation. In: IJCAI (2018)
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016)
Zhang, Z., Song, Y., Qi, H.: Age progression/regression by conditional adversarial autoencoder. In: CVPR (2017)
Zhang, Y., Liu, L., Li, C., et al.: Quantifying facial age by posterior of age comparisons. arXiv preprint arXiv:1708.09687 (2017)
Zhang, Z., Song, Y., Qi, H.: Age progression/regression by conditional adversarial autoencoder. In: CVPR (2017)
Acknowledgement
This work is partially funded by National Natural Science Foundation of China (Grant No. U1836217) and Shandong Provincial Key Research and Development Program (Major Scientific and Technological Innovation Project) (NO.2019JZZY010119).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Li, P., Huang, H., Hu, Y., Wu, X., He, R., Sun, Z. (2020). Hierarchical Face Aging Through Disentangled Latent Characteristics. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science(), vol 12348. Springer, Cham. https://doi.org/10.1007/978-3-030-58580-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-58580-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-58579-2
Online ISBN: 978-3-030-58580-8
eBook Packages: Computer ScienceComputer Science (R0)