The Study of Fashion Items Generation Based on Big Data and Deep Learning

Authors

  • Yang Song
  • Zhijian Wang
  • Jianming Zhang
  • Yan Wang

DOI:

https://doi.org/10.57118/creosar/978-1-915740-01-4_1

Keywords:

Fashion Design, Big Data, Generative Adversarial Networks, Disentangled Generator

Abstract

Since the Third Industrial Revolution, computer network information technology has made continuous progress, and the era of big data and Artificial Intelligence (AI) has arrived. The rapid progress of big data and AI will not only be able to promote the continuous improvement of computer network information technology, but also improve the level of economic development and make positive contributions. In this chapter, we propose a style-based fashion items generator for clothing design with big data and deep learning. Designing a clothing item is complicated, time-consuming, and challenging for clothes designers and clothing industry; however, recent improvements in conditional image generation provide a feasible solution. With a desired fashion category, the proposed framework will generate a nonexistent fashion item which cannot be distinguished from the real ones. Generative adversarial networks (GANs) make it possible to perform our clothing design with semi-supervised conditions. Our method can generate clothing items conditioned on 15 fashion categories. Furthermore, due to the multimodality of the clothes images, we employ a style-based generator with disentangled networks and adopt a multistage discriminator to improve the results of image generation. The effectiveness of our approach is well demonstrated through quantitative experiments. Our method will spark inspirations for fashion designers in their work.

References

G. Adomavicius and A. Tuzhilin, “Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions.” Knowledge and Data Engineering, IEEE Transactions, vol. 17, pp.734–749, July 2005.

A. McAfee, E. Brynjolfsson, T.H. Davenport, D.J. Patil, D. Barton, “Big data: The management revolution.” Harvard Bus Rev., vol. 90(10), pp. 61-70, Oct. 2012.

J. Manyika, M. Chui, B. Brown, J. Bughin, R. Dobbs, C. Roxburgh, A.H. Byers, “Big data: The next frontier for innovation, competition, and productivity,” McKinsey Global Institute, McKinsey & Company, May, 2011.

S. Lohr, “The age of big data,” New York Times, 11(2012).

L.C. Wang, X.Y.Zeng, L. Koehl, Y. Chen, “Intelligent fashion recommender system: Fuzzy logic in personalized garment design.,” IEEE Transactions on Human-Machine Systems, vol.45(1), pp.95-109, Feb. 2015.

H.T. Zheng, K.F. Wu, J. Park, W. Zhu, and J. Luo, “Personalized Fashion Recommendation from Personal Social Media Data: An Item-to-Set Metric Learning Approach,” in 2021 IEEE International Conference on Big Data, Orlando, FL, USA, 2021, pp. 5014-5023.

A. Borràs, F. Tous, J. Lladós, and M. Vanrell, “High-Level Clothes Description Based on Colour-Texture and Structural Features,” IbPRIA 2003, LNCS 2652, 2003, pp. 108–116.

T. He and Y. Hu. (2018, Oct.). “FashionNet: Personalized Outfit Recommendation with Deep Neural Network”. cs.CV [Online]. Available:https://arxiv.org/pdf/1810.02443v1.pdf

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," In Conf.Advances in Neural Information Processing Systems 27 (NIPS) , Montreal, QC, Canada, 2014, pp. 2672-2680.

M. Gygli, H. Grabner, H. Riemenschneider, F. Nater, and L. V. Gool. “The Interestingness of Images,” In: IEEE International Conference on Computer Vision (ICCV), Sydney, Australia, 2013, pp.1633–1640.

H. Yang, R. Zhang, X. Guo, W. Liu, W. Zuo, and P. Luo, "Towards photo-realistic virtual try-on by adaptively generating-preserving image content," In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, 2020, pp. 7847-7856.

Y. Taigman, A. Polyak, and L. Wolf, (2016, Nov.). “Unsupervised cross-domain image generation,” arXiv preprint arXiv:1611.02200, Available:https://arxiv.org/abs/1611.02200

A. Sage, E. Agustsson, R. Timofte, and L. Van Gool, “Logo synthesis and manipulation with clustered generative adversarial networks,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 5879–5888.

T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, "Improved techniques for training GANs,", Barcelona, Spain, 2016, pp. 2234-2242.

B. Uria, M. Cote, K. Gregor, I. Murray, and H. Larochelle, "Neural autoregressive distribution estimation," Journal of Machine Learning Research, vol. 17, pp. 1-37, Jan. 2016.

W. Chen, B. Zhao, P. Huang, J.M. Xu, X. Guo, C. Guo, F. Sun, C. Li, A. Pfadler, and H. Zhao. " POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion." in the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 2662–2670.

T. Wang, M. Liu, J. Zhu, A. Tao, J. Kautz, and B. Catanzaro, "High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs,", in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, UT, United states, 2018, pp. 8798-8807.

Y. Alharbi, P. Wonka, “Disentangled image generation through structured noise injection,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, United states, 2020, pp.5133-5141.

C. Lassner, G. Pons-Moll and P. V. Gehler, "A Generative Model of People in Clothing," in IEEE International Conference on Computer Vision,Venice, Italy, 2017, pp. 853-862.

W. Chen, B. Zhao, P. Huang, J.M. Xu, X. Guo, C. Guo, F. Sun, C. Li, A. Pfadler, and H. Zhao. " POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion." in the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 2662–2670.

L. Ma, X. Jia, Q. Sun, B. Schiele, T. Tuytelaars, and L. Van Gool, "Pose guided person image generation," in Proceedings of 31st Conference on Neural Information Processing Systems, Long Beach, CA, United states, 2017, pp. 406-416.

M. W. Gondal, B. Scholkopf and M. Hirsch, "The unreasonable effectiveness of texture transfer for single image super-resolution,", in European Conference on Computer Vision, Munich, Germany, 2019, pp. 80-97.

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image quality assessment: From error visibility to structural similarity," IEEE Transactions on Image Processing, vol. 13, pp. 600-612, Jan. 2004.

S. Reed, Z. Akata, X. Yan, L. Logeswaran, B. Schiele, and H. Lee, “Generative adversarial text to image synthesis,” in International Conference on Machine Learning (ICML), New York, NY, USA, 2016, pp. 81-90.

K. Tero, S. Laine, T. Aila, “A style-based generator architecture for generative adversarial networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.43(12), pp.4217-4228, 2021.

Y. Ren, X. Yu, J. Chen, et al., “Deep image spatial transformation for person image generation,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, United states, 2020, pp.7687-7696.

Y. Shen, J. Liang, M.C. Lin, “GAN-based garment generation using sewing pattern images,” in Computer Vision – ECCV, A. Vedaldi, H. Bischof, T. Brox, J.M. Frahm, Cham.: Springer, 2020, pp.225-247.

T. Park, J.Y. Zhu, O. Wang, J.W. Lu, E. Shechtman, A. Efros, and R. Zhang, “Swapping autoencoder for deep image manipulation,” in Proceedings of Advances in Neural Information Processing Systems (NeurIPS), online, 2020, pp.1-14.

L.C. Yang, S.Y. Chou, and Y.H. Yang,“Midinet: A convolutional generative adversarial network for symbolic-domain music generation,” in conference of International Society of Music Information Retrieval, eprint arXiv:1703.10847, March 2017.

Q. Zou, Z. Zhang, Q. Wang, Q.Q, Li, L. Chen, and S. Wang, “Who Leads the Clothing Fashion: Style, Color, or Texture? A Computational Study,” eprint arXiv:1608.07444, August 2016.

L.C. Wang, X.Y. Zeng, L. Koehl, Y. Chen, “Intelligent fashion recommender system: Fuzzy logic in personalized garment design” IEEE Transactions on Human-Machine Systems, vol.45(1), pp.95-109, Feb. 2015.

Published

2022-10-14

How to Cite

Song, Y., Wang, Z., Zhang, J., & Wang, Y. (2022). The Study of Fashion Items Generation Based on Big Data and Deep Learning. Artificial Intelligence Impressions, 1, 3–20. https://doi.org/10.57118/creosar/978-1-915740-01-4_1