Abstract
Global face attributes like Gender, Ethnicity, and Age are attracting attention due to their specific explanation of human faces. Mostly prior face attribute alteration works are on large-scale CelebA and LFW dataset. We address more challenging problem called global face attribute alteration on data sets like CLF and UTKFace. Our approach is based on sampling with global condition attribute. It consists of five components Encoder (\(E_{Z}\)), Encoder (\(E{_Y}\)), Sampling (S), Latent Space (ZL), and Decoder (D). The \(E{_Z}\) with S component is responsible to generate structured latent vector Z and \(E_{Y}\) produces condition vector L which we modify according to desired condition, latent vector Z and modified condition vector L are concatenated to make Latent Space ZL to help global face attribute alteration and Decoder D is used to generate modified images. We trained our SCDAE (Sampling and Condition based Deep AutoEncoder) model for gender and ethnicity alteration on CLF and UTKFace dataset. Both qualitative and quantitative experiments show that our approach can alter untouched global attributes and generates more realistic faces in term of person identity and age uniformity which is comparable to human observation.
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
Hinton, G., Salakhutdinov, R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: ICLR (2014)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27, pp. 2672–2680. Curran Associates Inc. (2014)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: ICLR (2016)
Zhu, J., Krähenbühl, P., Shechtman, E., Efros, A.A.: Generative visual manipulation on the natural image manifold. CoRR, vol. abs/1609.03552 (2016)
Xu, Z., Yang, X., Li, X., Sun, X.: The effectiveness of instance normalization: a strong baseline for single image dehazing. CoRR, vol. abs/1805.03305 (2018)
Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. CoRR, vol. abs/1508.06576 (2015)
Shi, Y., Debayan, D., Jain, A.K.: WarpGAN: automatic caricature generation (2018)
Reed, S.E., Akata, Z., Yan, X., Logeswaran, L., Schiele, B., Lee, H.: Generative adversarial text to image synthesis. CoRR, vol. abs/1605.05396 (2016)
Mirza, M., Osindero, S.: Conditional generative adversarial nets. CoRR, vol. abs/1411.1784 (2014)
Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV) (2015)
Huang, G.B., Mattar, M., Lee, H., Learned-Miller, E.: Learning to align from scratch. In: NIPS (2012)
Kumar, N., Berg, A.C., Belhumeur, P.N., Nayar, S.K.: Attribute and simile classifiers for face verification. In: IEEE International Conference on Computer Vision ICCV (2009)
Kumar, N., Belhumeur, P., Nayar, S.: FaceTracer: a search engine for large collections of images with faces. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5305, pp. 340–353. Springer, Berlin (2008). https://doi.org/10.1007/978-3-540-88693-8_25
Chandaliya, P.K., Garg, P., Nain, N.: Retrieval of facial images re-rendered with natural aging effect using child facial image and age. In: The 14th International Conference on Signal Image Technology and Internet Based System, Spain, 26–29 November 2018, pp. 457–464 (2018)
Song, Y., Zhang, Z., Qi, H.: Age progression/regression by conditional adversarial autoencoder. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2017)
Deb, D., Nain, N., Jain, A.K.: Longitudinal study of child face recognition. In: 2018 International Conference on Biometrics, ICB 2018, Gold Coast, Australia, 20–23 February 2018, pp. 225–232 (2018)
Zhang, Z., Song, Y., Qi, H.: Age progression/regression by conditional adversarial autoencoder. In: CVPR, pp. 4352–4360. IEEE Computer Society (2017)
Zheng, X., Guo, Y., Huang, H., Li, Y., He, R.: A survey to deep facial attribute analysis. CoRR, vol. abs/1812.10265 (2018)
Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. CoRR, vol. abs/1606.03657 (2016)
Li, M., Zuo, W., Zhang, D.: Deep identity-aware transfer of facial attributes. CoRR, vol. abs/1610.05586 (2016)
Liu, M., Breuel, T., Kautz, J.: Unsupervised image-to-image translation networks. CoRR, vol. abs/1703.00848 (2017)
Shen, W., Liu, R.: Learning residual images for face attribute manipulation. CoRR, vol. abs/1612.05363 (2016)
Wang, Y., Wang, S., Qi, G., Tang, J., Li, B.: Weakly supervised facial attribute manipulation via deep adversarial network. In: WACV, pp. 112–121. IEEE Computer Society (2018)
Zhang, G., Kan, M., Shan, S., Chen, X.: Generative adversarial network with spatial attention for face attribute editing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 422–437. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01231-1_26
Larsen, A.B.L., Sønderby, S.K., Winther, O.: Autoencoding beyond pixels using a learned similarity metric. CoRR, vol. abs/1512.09300 (2015)
Yan, X., Yang, J., Sohn, K., Lee, H.: Attribute2Image: conditional image generation from visual attributes. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 776–791. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46493-0_47
Perarnau, G., van de Weijer, J., Raducanu, B., Álvarez, J.M.: Invertible conditional GANs for image editing. CoRR, vol. abs/1611.06355 (2016)
Lample, G., Zeghidour, N., Usunier, N., Bordes, A., Denoyer, L., Ranzato, M.: Fader networks: manipulating images by sliding attributes, pp. 5969–5978 (2017)
Chandaliya, P.K., Nain, N.: Conditional perceptual adversarial variational autoencoder for age progression and regression on children face. In: The 12th IAPR International Conference On Biometrics, Crete Greece, 4–7 June 2019, pp. 200–208 (2019)
Lu, Y., Tai, Y.-W., Tang, C.-K.: Attribute-guided face generation using conditional cycleGAN. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 293–308. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_18
Choi, Y., Choi, M., Kim, M., Ha, J., Kim, S., Choo, J.: StarGAN: unified generative adversarial networks for multi-domain image-to-image translation. In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, 18–22 June 2018, pp. 8789–8797 (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)
Faceplus. https://www.faceplusplus.com
Acknowledgments
We gratefully acknowledge the support of NVIDIA Corporation with the donation of the TITAN V GPU used for this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chandaliya, P.K., Kumar, V., Harjani, M., Nain, N. (2020). SCDAE: Ethnicity and Gender Alteration on CLF and UTKFace Dataset. In: Nain, N., Vipparthi, S., Raman, B. (eds) Computer Vision and Image Processing. CVIP 2019. Communications in Computer and Information Science, vol 1148. Springer, Singapore. https://doi.org/10.1007/978-981-15-4018-9_27
Download citation
DOI: https://doi.org/10.1007/978-981-15-4018-9_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-4017-2
Online ISBN: 978-981-15-4018-9
eBook Packages: Computer ScienceComputer Science (R0)