Journal of the Korean Society of Clothing and Textiles (한국의류학회지)

The Korean Society of Clothing and Textiles (한국의류학회)
권호 표지
DOI QR코드

DOI QR Code

Deep Learning for Classification of High-End Fashion Brand Sensibility

딥러닝을 통한 하이엔드 패션 브랜드 감성 학습

  • Jang, Seyoon (Dept. of Research Institute of Human Ecology, Seoul National University) ;
  • Kim, Ha Youn (Dept. of Clothing & Textiles, Kunsan National University) ;
  • Lee, Yuri (Dept. of Textiles, Merchandising, and Fashion Design, Seoul National University/Research Institute of Human Ecology, Seoul National University) ;
  • Seol, Jinseok (Dept. of Computer Science and Engineering, Seoul National University) ;
  • Kim, Seongjae (Dept. of Computer Science and Engineering, Seoul National University) ;
  • Lee, Sang-goo (Dept. of Computer Science and Engineering, Seoul National University)
  • 장세윤 (서울대학교 생활과학연구소) ;
  • 김하연 (군산대학교 의류학과) ;
  • 이유리 (서울대학교 의류학과/서울대학교 생활과학연구소) ;
  • 설진석 (서울대학교 컴퓨터공학부) ;
  • 김성재 (서울대학교 컴퓨터공학부) ;
  • 이상구 (서울대학교 컴퓨터공학부)
  • Received : 2021.11.25
  • Accepted : 2022.01.25
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

The fashion industry is creating innovative business models using artificial intelligence. To efficiently utilize artificial intelligence (AI), fashion data must be classified. Until now, such data have been classified focusing only on the objective properties of fashion products. Their subjective attributes, such as fashion brand sensibilities, are holistic and heuristic intuitions created by a combination of design elements. This study aims to improve the performance of collaborative filtering in the fashion industry by extracting fashion brand sensibility using computer vision technology. The image data set of fashion brand sensibility consists of high-end fashion brand photos that share sensibilities and communicate well in fashion. About 26,000 fashion photos of 11 high-end fashion brand sensibility labels have been collected from the 16FW to 21SS runway and 50 years of US Vogue magazines beginning from 1971. We use EfficientNet-B1 to establish the main architecture and fine-tune the network with ImageNet-ILSVRC. After training fashion brand sensibilities through deep learning, the proposed model achieved an F-1 score of 74% on accuracy tests. Furthermore, as a result of comparing AI machine and human experts, the proposed model is expected to be expanded to mass fashion brands.

Keywords

Acknowledgement

This work was supported by the Korea Creative Contents Agency funded by the Korean Government (R2020040102, Technology development of intelligent fashion demand prediction and market analysis to improve fashion design for small business owners).

References

  1. Aaker, J. L. (1997). Dimensions of brand personality. Journal of Marketing Research, 34(3), 347-356. doi:10.1177/002224379703400304
  2. Abu-Bader, S. H. (2021). Using statistical methods in social science research: With a complete SPSS guide (3rd ed.). New York, NY: Oxford University Press.
  3. Ahmed, O. (2021, June 7). Balenciaga just staged a deep-fake SS22 fashion show. i-D. Retrieved from https://i-d.vice.com/en_uk/article/akg3bb/balenciaga-ss22-show-review
  4. Aldamiz-echevarria, G. (2018, January 30). How we grew from 0 to 4 million women on our fashion app, with a vertical machine learning approach. Medium. Retrieved from https://medium.com/hackernoon/how-we-grew-from-0-to-4-million-women-on-our-fashion-app-with-a-vertical-machine-learning-approach-f8b7fc0a89d7
  5. An, H., Kwon, S., & Park, M. (2019). A case study on the recommendation services for customized fashion styles based on artificial intelligence. Journal of the Korean Society of Clothing and Textiles, 43(3), 349-360. doi:10.5850/JKSCT.2019.43.3.349
  6. Barron, L. (2021). The return of the celebrity fashion muse: Brand endorsement, creative inspiration and celebrity-influenced design communication. Fashion Theory, 25(6), 757-776. doi:10.1080/1362704X.2019.1656946
  7. Carpenter, J. M., Moore, M., & Fairhurst, A. E. (2005). Consumer shopping value for retail brands. Journal of Fashion Marketing and Management, 9(1), 43-53. doi:10.1108/13612020510586398
  8. Chae, J. M., & Kim, E. H. (2020). Sales pattern and related product attributes of T-shirts. Journal of the Korean Society of Clothing and Textiles, 44(6), 1053-1069. doi:10.5850/JKSCT.2020.44.6.1053
  9. Chakraborty, S., Hoque, S. M. A., & Kabir, S. M. F. (2020). Predicting fashion trend using runway images: application of logistic regression in trend forecasting. International Journal of Fashion Design, Technology and Education, 13(3), 376-386. doi:10.1080/17543266.2020.1829096
  10. Cheerla, A., & Gevaert, O. (2019). Deep learning with multimodal representation for pancancer prognosis prediction. Bioinformatics, 35(14), i446-i454. doi:10.1093/bioinformatics/btz342
  11. Chen, H., Gallagher, A., & Girod, B. (2012). Describing clothing by semantic attributes. In A. Fitzgibbon, S. Lazebnik, P. Perona, Y. Sato, & C. Schmid (Eds.), Computer vision - ECCV 2012 12th European Conference on Computer Vision, Florence, Italy, October 7-13, 2012, Proceedings, Part III (pp. 609-623). Berlin and Heidelberg: Springer. doi:10.1007/978-3-642-33712-3_44
  12. Cheng, C.-I., & Liu, D. S.-M. (2008). An intelligent clothes search system based on fashion styles. Proceedings of 2008 International Conference on Machine Learning and Cybernetics, 3, China, 1592-1597. doi:10.1109/ICMLC.2008.4620660
  13. Cho, E., & Fiore, A. M. (2015). Conceptualization of a holistic brand image measure for fashion-related brands. Journal of Consumer Marketing, 32(4), 255-265. doi:10.1108/JCM07-2014-1063
  14. Choi, S.-L., Do, W.-H., & Lee, M.-S. (2018). Analysis of the constructional components of Chanel jacket design. Fashion & Textile Research Journal, 20(3), 266-278. doi:10.5805/SFTI.2018.20.3.266
  15. Clarke, D. W., Perry, P., & Denson, H. (2012). The sensory retail environment of small fashion boutiques. Journal of Fashion Marketing and Management, 16(4), 492-510. doi:10.1108/13612021211265872
  16. Cooper, G. (2019, October 3). New vision technologies for real-world applications. Semiconductor Engineering. Retrieved from https://semiengineering.com/new-vision-technologiesfor-real-world-applications/
  17. Copeland, L., Ciampaglia, G. L., & Zhao, L. (2019). Fashion informatics and the network of fashion knockoffs. First Monday, 24(12). doi:10.5210/fm.v24i12.9703
  18. DuBreuil, M., & Lu, S. (2020). Traditional vs. big-data fashion trend forecasting: an examination using WGSN and EDITED. International Journal of Fashion Design, Technology and Education, 13(1), 68-77. doi:10.1080/17543266.2020.1732482
  19. Escalas, J. E., & Bettman, J. R. (2005). Self-construal, reference groups, and brand meaning. Journal of Consumer Research, 32(3), 378-389. doi:10.1086/497549
  20. Eshwar, S. G., Gautham Ganesh Prabhu, J., Rishikesh, A. V., Charan, N. A., & Umadevi, V. (2016). Apparel classification using convolutional neural networks. Proceedings of 2016 International Conference on ICT in Business Industry & Government (ICTBIG), India, 1-5. doi:10.1109/ICTBIG.2016.7892641
  21. Fionda, A. M., & Moore, C. M. (2009). The anatomy of the luxury fashion brand. Journal of Brand Management, 16(5-6), 347-363. doi:10.1057/bm.2008.45
  22. Goutte, C., & Gaussier, E. (2005). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. In D. E. Losada & J. M. Fernandez-Luna (Eds), Advances in information retrieval: 27th European Conference on IR Research, ECIR 2005, Santiago de Compostela, Spain, March 21-23, 2005, Proceedings (pp. 345-359). Berlin and Heidelberg: Springer. doi:10.1007/978-3-540-31865-1_25
  23. Hines, T., & Bruce, M. (2007). Fashion marketing: Contemporary issues (2nd ed.). Oxford and Burlington: Butterworth-Heinemann..
  24. Hong, T., Kim, J., & Shin, J. (2016). A user sentiment classification using Instagram image and text analysis. Smart Media Journal, 5(1), 61-68.
  25. Israeli, A., & Avery, J. (2018, March 19). Predicting consumer tastes with big data at Gap. Harvard Business School. Retrieved from https://mycourses.aalto.fi/pluginfile.php/1458535/mod_folder/intro/CASE%20GAP%20Predicting%20consumer%20tastes.pdf
  26. Jia, M., Shi, M., Sirotenko, M., Cui, Y., Hariharan, B., Cardie, C., & Belongie, S. (2019, June 17). The fashionpedia ontology and fashion segmentation dataset. CVPR Workshop on Fine-Grained Visual Categorization Workshops (FGVC), Long Beach, CA. Retrieved from https://vision.cornell.edu/se3/wp-content/uploads/2019/06/Fashionpedia_TechReport.pdf
  27. Jin, L., & Liang, H. (2017). Deep learning for underwater image recognition in small sample size situations. Proceedings of OCEANS 2017 - Aberdeen, UK, 1-4. doi:10.1109/OCEANSE.2017.8084645
  28. Jung, J. H. (2021, September 15). "인공지능, 스니커즈를 디자인하다".… AI SNEAKERS 'AIKERS' 선보여 ["AI designs sneakers", showed AI SNEAKERS 'AIKERS']. Biz World. Retrieved from https://www.bizwnews.com/news/articleView.html?idxno=27594
  29. Keller, K. L. (2003). Understanding brands, branding and brand equity. Interactive Marketing, 5(1), 7-20. doi:10.1057/palgrave.im.4340213
  30. Keller, K. L., & Swaminathan, V. (2020). Strategic brand management: Building, measuring, and managing brand equity (5th ed.). Harlow: Pearson.
  31. Kiapour, M. H., Yamaguchi, K., Berg, A. C., & Berg, T. L. (2014). Hipster wars: Discovring elements of fashion styles. In D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars (Eds.), Computer vision - ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part I (pp. 472-488). Cham: Springer. doi:10.1007/978-3-319-10590-1_31
  32. Kim, H.-S., & Cho, S.-B. (2000). Application of interactive genetic algorithms to fashion design. Engineering Applications of Artificial Intelligence, 13(6), 635-644. doi:10.1016/S0952-1976(00)00045-2
  33. Kim, H., Jang, S., Lee, Y., Seol, J., Kim, S., & Lee, S.-g. (2021). 딥러닝을 활용한 패션브랜드 감성 학습 [Deep learning for classification of fashion brand sensibility]. Proceedings of the Korean Society of Clothing and Textiles, Spring Conference, Korea, 128.
  34. Kim, Y. J. (2021, April 1). AI가 옷디자인 한다…ETRI 'AI 디자이너, 모델생성기술' 개발 [AI designs clothes…ETRI Development of 'AI designer, model generation technology']. Electronic Time Internet. Retrieved from https://m.etnews.com/20210401000112?obj=Tzo4OiJzdGRDbGFzcyI6Mjp7czo3OiJyZWZlcmVyIjtOO3M6NzoiZm9yd2FyZCI7czoxMzoid2ViIHRvIG1vYmlsZSI7fQ%3D%3D
  35. Kingma, D. P., & Ba, J. L. (2015, May 7-9). Adam: A method for stochastic optimization. 3rd International Conference for Learning Representations, San Diego, CA. Retrieved from https://click.endnote.com/viewer?doi=arxiv%3A1412.6980&token=WzMwMDE1OTIsImFyeGl2OjE0MTIuNjk4MCJd.qJIHf8g_nDAIDH15NLTHf7swjWY
  36. Ko, E., Lee, M. A., & Lee, M. (2012). Fashion brand & communication. Paju: Kyomunsa.
  37. Kwon, S., Choi, Y., Kim, S., & An, H. (2020). Fashion style classification of SNS images using convolutional neural networks. Proceedings of 2020 International Conference on Clothing and Textiles (ICCT), Korea, 40-41.
  38. Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017). Building machines that learn and think like people. Behavioral and Brain Sciences, 40:e253. doi:10.1017/S0140525X16001837
  39. Lee, H., Seol, J., & Lee, S.-g. (2017, August 14). Style2Vec: Representation learning for fashion items from style sets. Cornell University. Retrieved from https://arxiv.org/abs/1708.04014
  40. Lee, I., & Shin, Y. J. (2020). Machine learning for enterprises: Applications, algorithm selection, and challenges. Business Horizons, 63(2), 157-170. doi:10.1016/j.bushor.2019.10.005
  41. Lee, K. M. (2018). Artificial intelligence. Paju: Life and Power Press.
  42. Lee, S., Kang, J. H., Lee, H. Joo, T. W., Oh, S., Park, S., & Kim, S. B. (2014). Prediction of product life cycle using data mining algorithms : A case study of clothing industry. Journal of the Korean Institute of Industrial Engineers, 40(3), 291-298. doi:10.7232/JKIIE.2014.40.3.291
  43. Liang, X., Liu, S., Shen, X., Yang, J., Liu, L., Dong, J., ... Yan, S. (2015). Deep human parsing with active template regression. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(12), 2402-2414. doi:10.1109/TPAMI.2015.2408360
  44. Lin, Y., & Yang, H. (2019, July 16). Predicting next-season designs on high fashion runway. Cornell University. Retrieved from https://arxiv.org/abs/1907.07161
  45. Liu, F., Li, J., Mizerski, D., & Soh, H. (2012). Self-congruity, brand attitude, and brand loyalty: a study on luxury brands. European Journal of Marketing, 46(7/8), 922-937. doi:10.1108/03090561211230098
  46. Liu, Z., Luo, P., Qiu, S., Wang, X., & Tang, X. (2016). DeepFashion: Powering robust clothes recognition and retrieval with rich annotations. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), USA, 1096-1104. doi:10.1109/CVPR.2016.124
  47. Ma, Y., Jia, J., Zhou, S., Fu, J., Liu, Y., & Tong, Z. (2017). Towards better understanding the clothing fashion styles: A multimodal deep learning approach. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 31(1), USA, 38-44.
  48. MarketsandMarketsTM. (2019, October). AI in fashion market by component (solutions and services), application(product recommendation, product search & discovery, and CRM), deployment mode, category, (apparel, accessories, and beauty & cosmetics), end user, and region - global forecast to 2024. MarketsandMarkets. Retrieved from https://www.marketsandmarkets.com/Market-Reports/ai-in-fashion-market-144448991.html
  49. McCracken, G. D. (1985). The trickle-down theory rehabilitated. In M. R. Solomon (Ed.), The psychology of fashion (pp. 39-54). Lexington, MA: Lexington Books.
  50. McQuarrie, E. F., & Phillips, B. J. (2008). It's not your father's magazine ad: Magnitude and direction of recent changes in advertising style. Journal of Advertising, 37(3), 95-106. doi:10.2753/JOA0091-3367370307
  51. Mello, P., Storari, S., & Valli, B. (2008). A knowledge-based system for fashion trend forecasting. In N. T. Nguyen, L. Borzemski, A. Grzech, & M. Ali (Eds.), New frontiers in applied artificial intelligence: 21st International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2008 Wroclaw, Poland, June 18-20, 2008 Proceedings (pp. 425-434). Berlin and Heidelberg: Springer. doi:10.1007/978-3-540-69052-8_45
  52. Park, S., Shin, M., Ham, S., Choe, S., & Kang, Y. (2019). Study on fashion image retrieval methods for efficient fashion visual search. Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPR), USA, 316-319. doi:10.1109/CVPRW.2019.00042
  53. Phillips, B. J., McQuarrie, E. F., & Griffin, W. G. (2014). How visual brand identity shapes consumer response. Psychology & Marketing, 31(3), 225-236. doi:10.1002/mar.20689
  54. Ramachandran, P., Zoph, B., & Le, Q. V. (2017, October 27). Swish: A self-gated activation function. Cornell University. Retrieved from https://arxiv.org/abs/1710.05941v1
  55. Rashid, K. M., & Louis, J. (2019). Times-series data augmentation and deep learning for construction equipment activity recognition. Advanced Engineering Informatics, 47:100944. doi:10.1016/j.aei.2019.100944
  56. Ross, J., & Harradine, R. (2011). Fashion value brands: the relationship between identity and image. Journal of Fashion Marketing and Management, 15(3), 306-325. doi:10.1108/13612021111151914
  57. Sadeh, G., Fritz, L., Shalev, G., & Oks, E. (2019, June 15). Joint visual-textual embedding for multimodal style search. Cornell University. Retrieved from https://arxiv.org/abs/1906.06620
  58. Schneider, S., Greenberg, S., Taylor, G. W., & Kremer, S. C. (2020). Three critical factors affecting automated image species recognition performance for camera traps. Ecology and Evolution, 10(7), 3503-3517. doi:10.1002/ece3.6147
  59. Schwab, K. (2018, August 22). This AI designs Balenciaga better than Balenciaga. Fast Company. Retrieved from https://www.fastcompany.com/90223486/this-ai-designs-balencia ga-better-than-balenciaga
  60. Seo, Y.,. & Shin, K.-s. (2018). Business application of convolutional neural networks for apparel classification using runway image. Journal of Intelligence and Information Systems, 24(3), 1-19. doi:10.13088/jiis.2018.24.3.001
  61. Standish, J., & Ganapathy, V. (2018, December 27). Think tank: How AI can power the future of fashion. WWD. Retrieved from https://wwd.com/business-news/business-features/jill-standish-think-tank-1202941433/
  62. Svendsen, L. (2006). Fashion: A philosophy (J. Irons, Trans). London: Reaktion Books. (Original work published 2004)
  63. Takagi, M., Simo-Serra, E., Iizuka, S., & Ishikawa, H. (2017). What makes a style: Experimental analysis of fashion prediction. Proceedings of 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Italy, 2247-2253. doi:10.1109/ICCVW.2017.263
  64. Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, USA, 6105-6114.
  65. Taste graphs will transform fashion - Fashion Taste API. (2019, April 10). Chicisimo. Retrieved from https://blog.chicisimo.com/2019/04/10/taste-graphs-fashion/
  66. Teo, M. (2018, October 23). How Coco Chanel revolutionised women's fashion with just a jacket. Lifestyle Asia. Retrieved from https://www.lifestyleasia.com/sg/style/fashion/how-coco-chanel-revolutionised-womens-fashion-with-just-a-jacket/
  67. Tokumaru, M., Muranaka, N., & Imanishi, S. (2003). Virtual Stylist project - examination of adapting clothing search system to user's subjectivity with interactive genetic algorithms. Proceedings of The 2003 Congress on Evolutionary Computation '03, 2, Australia, 1036-1043. doi:10.1109/CEC.2003.1299782
  68. Wang, N., & Ai, H. (2011). Who Blocks Who: Simultaneous clothing segmentation for grouping images. Proceedings of 2011 International Conference on Computer Vision, Spain, 1535-1542. doi:10.1109/ICCV.2011.6126412
  69. Yun, S. Y., Kim, S., & Park, C. K. (2009). Development of an expert system for optimum fusible interlining. Journal of the Korean Society for Clothing Industry, 11(4), 648-660.
  70. Zhang, L., Hu, C., Chen, Q., Chen, Y., & Shi, Y. (2012). Domain knowledge based personalized recommendation model and its application in cross-selling. Procedia Computer Science, 9, 1314-1323. doi:10.1016/j.procs.2012.04.144