Abstract
Existing face sketch synthesis methods extend conditional generative adversarial network framework with promising performance. However, they usually pre-train on additional large-scale datasets, and the performance is still not satisfied. To tackle the issues, we develop a deep bidirectional network based on the least mean square error reconstruction (Lmser) self-organizing network, which is a further development of autoencoder by folding along the central hidden layer. Such folding makes the neurons on the paired layers between encoder and decoder merge into one. We model the photo-to-sketch mapping by an Lmser network and build a sketch-to-photo mapping by a complement Lmser sharing the same structure. The bidirectional mappings form an alternation system. We devise a supervised alternating consistency for the system, by minimizing the deviation between the alternatively mapped pattern and the ground-truth. Enhanced by the consistency constraints along the bidirectional paths, the model achieve a significant improvement in terms of Fréchet Inception Distance (FID). Experiments demonstrate the effectiveness of our method in comparison with state-of-the-art methods, and reduce the FID from 34.1 to 28.7 on the CUFS dataset and from 18.2 to 11.5 on the CUFSF dataset.
Supported by National Science and Technology Innovation 2030 Major Project (2018AAA0100700) of the Ministry of Science and Technology of China and Shanghai Municipal Science and Technology Major Project (2021SHZDZX0102).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Chen, D., Yuan, L., Liao, J., Yu, N., Hua, G.: Stylebank: an explicit representation for neural image style transfer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2770–2779 (2017)
Chen, L., Liao, H., Ko, M., Lin, J., Yu, G.: A new lda-based face recognition system which can solve the small sample size problem. Pattern Recogn. 33(10), 1713–1726 (2000)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27, pp. 2672–2680 (2014)
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, vol. 30, pp. 6626–6637 (2017)
Huang, W., Tu, S., Xu, L.: Revisit lmser from a deep learning perspective. In: Intelligence Science and Big Data Engineering. Big Data and Machine Learning, pp. 197–208 (2019)
Huang, W., Tu, S., Xu, L.: Deep CNN based Lmser and strengths of two built-in dualities. Neural Process. Lett. 8, 108418–108428 (2020)
Isola, P., Zhu, J., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5967–5976 (2017)
Johson, J., Alahi, A., Li, F.F.: Perceptual losses for real-time style transfer and super-resolution. In: European Conference on Computer Vision, pp. 694–711 (2016)
Karacan, L., Erdem, E., Erdem, A.: Structure-preserving image smoothing via region covariances 32(6), 176 (2013)
Li, P., Tu, S., Xu, L.: GAN flexible Lmser for super-resolution. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 756–764 (2019)
Liu, M., Tuzel, O.: Coupled generative adversarial networks. In: Advances in Neural Information Processing Systems, vol. 29, pp. 469–477 (2016)
Liu, Q., Tang, X., Jin, H., Lu, H., Ma, S.: A nonlinear approach for face sketch synthesis and recognition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 1005–1010 (2005)
Liu, S., Yang, J., Huang, C., Yang, M.: Multi-objective convolutional learning for face labeling. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3451–3459 (2015)
Lucic, M., Kurach, K., Michalski, M., Gelly, S., Bousquet, O.: Are gans created equal? a large-scale study. In: Advances in Neural Information Processing Systems, vol. 31, pp. 700–709 (2018)
Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B.: Adversarial autoencoders. arXiv preprint arXiv:1511.05644 (2015)
Mao, X., Li, Q., Xie, H., Lau, R.Y.K., Wang, Z., Smolley, S.P.: Least squares generative adversarial networks. In: IEEE International Conference on Computer Vision, pp. 2813–2821 (2017)
Martinez, A., Benavente, R.: The AR face database. CVC Technical Report #24 (1998)
Messer, K., Matas, J., Kittler, J., Luettin, J., Maitre, G.: XM2VTSDB: The extended M2VTS database. In: Second International Conference on Audio and Video-based Biometric Person Authentication, pp. 72–77 (1999)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Song, Y., Bao, L., Yang, Q., Yang, M.: Real-time exemplar-based face sketch synthesis. In: European Conference on Computer Vision, pp. 800–813 (2014)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Tang, X., Wang, X.: Face photo recognition using sketch. In: Proceedings of the International Conference on Image Processing, vol. 1, pp. I-I (2002)
Tang, X., Wang, X.: Face sketch synthesis and recognition. In: Proceedings Ninth IEEE International Conference on Computer Vision, vol. 1, pp. 687–694 (2003)
Wang, N., Gao, X., Li, J.: Random sampling for fast face sketch synthesis. Pattern Recogn. 76, 215–227 (2018)
Wang, N., Gao, X., Li, J., Song, B., Li, Z.: Evaluation on synthesized face sketches. Neurocomputing 214, 991–1000 (2016)
Wang, N., Zha, W., Li, J., Gao, X.: Back projection: an effective postprocessing method for GAN-based face sketch synthesis. Pattern Recogn. Lett. 107, 59–65 (2017)
Wang, X., Tang, X.: Face photo-sketch synthesis and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(11), 1955–1967 (2009)
Xu, L.: Least mse reconstruction by self-organization. i. multi-layer neural-nets. In: Proceedings 1991 IEEE International Joint Conference on Neural Networks, vol. 3, pp. 2362–2367 (1991)
Xu, L.: Least mean square error reconstruction principle for self-organizing neural-nets. Neural Netw. 6(5), 627–648 (1993)
Xu, L.: An overview and perspectives on bidirectional intelligence: Lmser duality, double IA harmony, and causal computation. IEEE/CAA J. Automatica Sinica 6(4), 865–893 (2019)
Yang, H., Tu, S.: Glmser: a gan-lmser network for image-to-image translation. In: IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), pp. 582–589 (2019)
Yu, J., et al.: Toward realistic face photo-sketch synthesis via composition-aided gans. IEEE Transactions on Cybernetics, pp. 1–13 (2020)
Zhang, D., Lin, L., Chen, T., Wu, X., Tan, W., Izquierdo, E.: Content-adaptive sketch portrait generation by decompositional representation learning. IEEE Trans. Image Process. 26(1), 328–339 (2017)
Zhang, L., Lin, L., Wu, X., Ding, S., Zhang, L.: End-to-end photo-sketch generation via fully convolutional representation learning. In: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, pp. 627–634 (2015)
Zhang, L., Zhang, L., Mou, X., Zhang, D.: FSIM: a feature similarity index for image quality assessment. IEEE Trans. Image Process. 20(8), 2378–2386 (2011)
Zhang, M., Li, J., Wang, N., Gao, X.: Compositional model-based sketch generator in facial entertainment. IEEE Trans. Syst. Man Cybern. 48(3), 904–915 (2018)
Zhang, W., Wang, X., Tang, X.: Coupled information-theoretic encoding for face photo-sketch recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 513–520 (2011)
Zhu, J., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: IEEE International Conference on Computer Vision, pp. 2242–2251 (2017)
Zhu, M., Wang, N., Gao, X., Li, J.: Deep graphical feature learning for face sketch synthesis. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, pp. 3574–3580 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Sheng, Q., Tu, S., Xu, L. (2021). A Consistency Enhanced Deep Lmser Network for Face Sketch Synthesis. In: Pham, D.N., Theeramunkong, T., Governatori, G., Liu, F. (eds) PRICAI 2021: Trends in Artificial Intelligence. PRICAI 2021. Lecture Notes in Computer Science(), vol 13031. Springer, Cham. https://doi.org/10.1007/978-3-030-89188-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-030-89188-6_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89187-9
Online ISBN: 978-3-030-89188-6
eBook Packages: Computer ScienceComputer Science (R0)