SizeNet: Weakly Supervised Learning of Visual Size and Fit in Fashion Images
This addresses the problem of finding clothes that fit for e-commerce customers, offering a novel visual approach to overcome the cold start issue for new articles.
The paper tackled the cold start problem in fashion e-commerce by using visual data to infer size and fit characteristics, proposing SizeNet, a weakly-supervised teacher-student framework that achieved results on thousands of garments from hundreds of brands.
Finding clothes that fit is a hot topic in the e-commerce fashion industry. Most approaches addressing this problem are based on statistical methods relying on historical data of articles purchased and returned to the store. Such approaches suffer from the cold start problem for the thousands of articles appearing on the shopping platforms every day, for which no prior purchase history is available. We propose to employ visual data to infer size and fit characteristics of fashion articles. We introduce SizeNet, a weakly-supervised teacher-student training framework that leverages the power of statistical models combined with the rich visual information from article images to learn visual cues for size and fit characteristics, capable of tackling the challenging cold start problem. Detailed experiments are performed on thousands of textile garments, including dresses, trousers, knitwear, tops, etc. from hundreds of different brands.