Fashion trends are constantly evolving, but a trained eye can estimate with some accuracy the signature elements of a particular designer's style. For this competition, we'd like to see how closely a machine learning model might do the same.
We have sampled 50,000 runway images, spanning 50 fashion designers, from our large repository of proprietary front row images from fashion shows over the past 15 years. The data includes a variety of fashion items, including: shoes, bags, dress, jackets etc.
In this competition, you will try to predict the designer of the article or ensemble shown in each image. By solving this challenge, you will help researchers and editors better understand the unique features or the nuances that distinguish fashion designers and define fashion trends over time.
Check out the Kaggle page for the competition, with additional info on Github.
Competition Begins 5 April 2019
Submission Deadline 31 May 2019
Hearst Magazine Media is the sponsor of the prizes:
1st place: $ 2,500
2nd place: $ 1,000
3rd place: $ 500
R.J. Lehman, Hearst Magazine Media
Hao Han, Hearst Magazine Media