iMat Fashion 2019
As part of the FGVC6 workshop at CVPR 2019 we are conducting the iMaterialist - Fashion track 2019 apparel instance segmentation & fine-grained attribute classification competition. The goal of this competition is to push the state of the art of the novel fine-grained segmentation task by joining forces between the fashion and computer vision communities. To capture the complex structure of fashion objects and ambiguity in descriptions obtained from crawling the web, our standardized taxonomy contains 46 apparel objects (27 main apparel items and 19 apparel parts), and 92 related fine-grained attributes. Secondly, a total of around 50k clothing images (10k with both segmentation and fine-grained attributes, 40k with apparel instance segmentation) in daily-life, celebrity events, and online shopping are labeled by both domain experts and crowd workers for fine-grained segmentation.
In this competition, we challenge you to develop algorithms that will help with an important step towards automatic product detection – to accurately assign segmentations and attribute labels for fashion images. Individuals/Teams with top submissions will be invited to present their work live at the FGVC6 workshop.
Menglin Jia (Cornell University)
Mengyun (David) Shi (Cornell University)
Mikhail Sirotenko (Google AI)
Serge Belongie (Cornell University and Cornell Tech)