Fork me on GitHub

Semantic segmentation of fashion images using feature pyramid networks

Our main objective is to facilitate fashion image analysis. We do this through semantic segmentation of fashion images, using both textural information and cues from shape and context, where target classes are clothing categories. Our main contributions are *state-of-the-art semantic segmentation of fashion images*, and *modest memory and GPU/CPU usage*.

John Martinsson, Olof Mogren

To be presented at Second Workshop on Computer Vision for Fashion, Art and Design at ICCV 2019.
PDF Fulltext bibtex.

Olof Mogren Research institutes of Sweden

LinkedIn Twitter Atom/RSS Feed