Transformer-based Graph Neural Networks for Outfit Generation

by   Federico Becattini, et al.

Suggesting complementary clothing items to compose an outfit is a process of emerging interest, yet it involves a fine understanding of fashion trends and visual aesthetics. Previous works have mainly focused on recommendation by scoring visual appeal and representing garments as ordered sequences or as collections of pairwise-compatible items. This limits the full usage of relations among clothes. We attempt to bridge the gap between outfit recommendation and generation by leveraging a graph-based representation of items in a collection. The work carried out in this paper, tries to build a bridge between outfit recommendation and generation, by discovering new appealing outfits starting from a collection of pre-existing ones. We propose a transformer-based architecture, named TGNN, which exploits multi-headed self attention to capture relations between clothing items in a graph as a message passing step in Convolutional Graph Neural Networks. Specifically, starting from a seed, i.e. one or more garments, outfit generation is performed by iteratively choosing the garment that is most compatible with the previously chosen ones. Extensive experimentations are conducted with two different datasets, demonstrating the capability of the model to perform seeded outfit generation as well as obtaining state of the art results on compatibility estimation tasks.


page 8

page 11


Dressing as a Whole: Outfit Compatibility Learning Based on Node-wise Graph Neural Networks

With the rapid development of fashion market, the customers' demands of ...

Improved Representation Learning for Session-based Recommendation

Session-based recommendation systems suggest relevant items to users by ...

Learning Furniture Compatibility with Graph Neural Networks

We propose a graph neural network (GNN) approach to the problem of predi...

Time Interval-enhanced Graph Neural Network for Shared-account Cross-domain Sequential Recommendation

Shared-account Cross-domain Sequential Recommendation (SCSR) task aims t...

VICTOR: Visual Incompatibility Detection with Transformers and Fashion-specific contrastive pre-training

For fashion outfits to be considered aesthetically pleasing, the garment...

Improving Outfit Recommendation with Co-supervision of Fashion Generation

The task of fashion recommendation includes two main challenges: visual ...

Please sign up or login with your details

Forgot password? Click here to reset