# SizeNet: Weakly Supervised Learning of Visual Size and Fit in Fashion Images

## TL;DR

SizeNet is a weakly supervised learning framework that uses visual data to predict size and fit of fashion items, addressing the cold start problem in e-commerce without relying solely on purchase history.

## Contribution

It introduces a novel teacher-student training approach that combines statistical models with visual cues to infer size and fit characteristics of fashion articles.

## Key findings

- Effective in predicting size and fit across diverse clothing types
- Addresses cold start problem by leveraging visual data
- Performs well on large, diverse dataset of garments

## Abstract

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.