Theme-Matters: Fashion Compatibility Learning via Theme Attention

TL;DR

This paper introduces a novel theme-aware fashion compatibility model that considers specific themes, such as 'dating' or 'business', to improve outfit compatibility assessment, supported by a new large-scale dataset and superior experimental results.

Contribution

It presents the first theme-conditioned fashion compatibility model and a new dataset with theme labels, enhancing outfit recommendation accuracy.

Findings

Our model outperforms existing methods in compatibility prediction.

The dataset includes 14K outfits and 40K items with detailed theme and category labels.

Theme-aware modeling significantly improves fashion compatibility assessment.

Abstract

Fashion compatibility learning is important to many fashion markets such as outfit composition and online fashion recommendation. Unlike previous work, we argue that fashion compatibility is not only a visual appearance compatible problem but also a theme-matters problem. An outfit, which consists of a set of fashion items (e.g., shirt, suit, shoes, etc.), is considered to be compatible for a "dating" event, yet maybe not for a "business" occasion. In this paper, we aim at solving the fashion compatibility problem given specific themes. To this end, we built the first real-world theme-aware fashion dataset comprising 14K around outfits labeled with 32 themes. In this dataset, there are more than 40K fashion items labeled with 152 fine-grained categories. We also propose an attention model learning fashion compatibility given a specific theme. It starts with a category-specific subspace learning, which projects compatible outfit items in certain categories to be close in the subspace. Thanks to strong connections between fashion themes and categories, we then build a theme-attention model over the category-specific embedding space. This model associates themes with the pairwise compatibility with attention, and thus compute the outfit-wise compatibility. To the best of our knowledge, this is the first attempt to estimate outfit compatibility conditional on a theme. We conduct extensive qualitative and quantitative experiments on our new dataset. Our method outperforms the state-of-the-art approaches.