Skip to main content
Top

Hint

Swipe to navigate through the chapters of this book

Published in:
Cover of the book

2018 | OriginalPaper | Chapter

Style Neutralization Generative Adversarial Classifier

Authors : Haochuan Jiang, Kaizhu Huang, Rui Zhang, Amir Hussain

Published in: Advances in Brain Inspired Cognitive Systems

Publisher: Springer International Publishing

share
SHARE

Abstract

Breathtaking improvement has been seen with the recently proposed deep Generative Adversarial Network (GAN). Purposes of most existing GAN-based models majorly concentrate on generating realistic and vivid patterns by a pattern generator with the aid of the binary discriminator. However, few study were related to the promotion of classification performance with merits of those generated ones. In this paper, a novel and generalized classification framework called Style Neutralization Generative Adversarial Classifier (SN-GAC), based on the GAN framework, is introduced to enhance the classification accuracy by neutralizing possible inconsistent style information existing in the original data. In the proposed model, the generator of SN-GAC is trained by mapping the original patterns with certain styles (source) to their style-neutralized or standard counterparts (standard-target), capable of generating the targeted style-neutralized one (generated-target). On the other hand, pairs of both standard (source + standard-target) and generated (source + generated-target) patterns are fed into the discriminator, optimized by not only distinguishing between real and fake, but also classifying the input pairs with correct class label assignment. Empirical experiments fully demonstrate the effectiveness of the proposed SN-GAC framework by achieving so-far the highest accuracy on two benchmark classification databases including the face and the Chinese handwriting character, outperforming several relevant state-of-the-art baseline approaches.
Footnotes
1
The discriminator with auxiliary classifier is termed as D-C in this paper since it differs from the D of traditional GAN as in [5]. Moreover, the proposed D-C is also different from [16] since the classifier in the SN-GAC model can be directly applied for normal classification after well trained. However, the auxiliary classifier in [16] is only utilized to provide supervising information for better GAN training.
 
2
The proposed SN-GAC model is evaluated only with dataset specifying groups of style patterns in this paper for the simplification purpose.
 
3
Paired input is not evaluated for conventional baselines in Sect. 3 since style-neutralization cannot be achieved with traditional approaches.
 
Literature
1.
go back to reference Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M.: TensorFlow: a system for large-scale machine learning. OSDI 16, 265–283 (2016) Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M.: TensorFlow: a system for large-scale machine learning. OSDI 16, 265–283 (2016)
3.
go back to reference Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995) MATH Cortes, C., Vapnik, V.: Support-vector networks. Mach. Learn. 20(3), 273–297 (1995) MATH
4.
go back to reference Evgeniou, T., Pontil, M.: Regularized multi-task learning. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 109–117. ACM (2004) Evgeniou, T., Pontil, M.: Regularized multi-task learning. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 109–117. ACM (2004)
5.
go back to reference Goodfellow, I., et al.: Generative adversarial nets. In: Advances in neural information processing systems, pp. 2672–2680 (2014) Goodfellow, I., et al.: Generative adversarial nets. In: Advances in neural information processing systems, pp. 2672–2680 (2014)
6.
go back to reference Gourier, N., Hall, D., Crowley, J.L.: Estimating face orientation from robust detection of salient facial structures. In: FG Net Workshop on Visual Observation of Deictic Gestures, vol. 6, p. 7 (2004) Gourier, N., Hall, D., Crowley, J.L.: Estimating face orientation from robust detection of salient facial structures. In: FG Net Workshop on Visual Observation of Deictic Gestures, vol. 6, p. 7 (2004)
8.
go back to reference Huang, K., Jiang, H., Zhang, X.Y.: Field support vector machines. IEEE Trans. Emerg. Top. Comput. Intell. 1(6), 454–463 (2017) CrossRef Huang, K., Jiang, H., Zhang, X.Y.: Field support vector machines. IEEE Trans. Emerg. Top. Comput. Intell. 1(6), 454–463 (2017) CrossRef
9.
go back to reference Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. arXiv preprint (2017) Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. arXiv preprint (2017)
11.
go back to reference Jiang, Y., Lian, Z., Tang, Y., Xiao, J.: DCFont: an end-to-end deep Chinese font generation system. In: SIGGRAPH Asia 2017 Technical Briefs, p. 22. ACM (2017) Jiang, Y., Lian, Z., Tang, Y., Xiao, J.: DCFont: an end-to-end deep Chinese font generation system. In: SIGGRAPH Asia 2017 Technical Briefs, p. 22. ACM (2017)
12.
go back to reference Jing, X.Y., Wong, H.S., Zhang, D.: Face recognition based on 2D fisherface approach. Pattern Recognit. 39(4), 707–710 (2006) CrossRef Jing, X.Y., Wong, H.S., Zhang, D.: Face recognition based on 2D fisherface approach. Pattern Recognit. 39(4), 707–710 (2006) CrossRef
14.
go back to reference Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012) Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
15.
go back to reference Liu, C.L., Yin, F., Wang, D.H., Wang, Q.F.: CASIA online and offline Chinese handwriting databases. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 37–41. IEEE (2011) Liu, C.L., Yin, F., Wang, D.H., Wang, Q.F.: CASIA online and offline Chinese handwriting databases. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 37–41. IEEE (2011)
17.
go back to reference Sarkar, P., Nagy, G.: Style consistent classification of isogenous patterns. IEEE Trans. Pattern Anal. Mach. Intell. 27(1), 88–98 (2005) CrossRef Sarkar, P., Nagy, G.: Style consistent classification of isogenous patterns. IEEE Trans. Pattern Anal. Mach. Intell. 27(1), 88–98 (2005) CrossRef
19.
go back to reference Tenenbaum, J.B., Freeman, W.T.: Separating style and content with bilinear models. Neural Comput. 12(6), 1247–1283 (2000) CrossRef Tenenbaum, J.B., Freeman, W.T.: Separating style and content with bilinear models. Neural Comput. 12(6), 1247–1283 (2000) CrossRef
21.
go back to reference Zhang, X.Y., Huang, K., Liu, C.L.: Pattern field classification with style normalized transformation. In: IJCAI Proceedings-International Joint Conference on Artificial Intelligence, vol. 22, p. 1621 (2011) Zhang, X.Y., Huang, K., Liu, C.L.: Pattern field classification with style normalized transformation. In: IJCAI Proceedings-International Joint Conference on Artificial Intelligence, vol. 22, p. 1621 (2011)
Metadata
Title
Style Neutralization Generative Adversarial Classifier
Authors
Haochuan Jiang
Kaizhu Huang
Rui Zhang
Amir Hussain
Copyright Year
2018
DOI
https://doi.org/10.1007/978-3-030-00563-4_1

Premium Partner