As shoppers move online, it’d be a dream come true to have products in photos classified automatically. But, automatic product recognition is challenging because for the same product, a picture can be taken in different lighting, angles, backgrounds, and levels of occlusion. Meanwhile different fine-grained categories may look very similar, for example, ball chair vs egg chair for furniture, or dutch oven vs french oven for cookware. Many of today’s general-purpose recognition machines simply can’t perceive such subtle differences between photos, yet these differences could be important for shopping decisions. Tackling issues like this is why the Conference on Computer Vision and Pattern Recognition (CVPR) has put together a workshop specifically for data scientists focused on fine-grained visual categorization called the FGVC5 workshop. As part of this workshop, CVPR is partnering with Google, Malong Technologies and Wish to challenge the data science community to help push the state of the art in automatic image classification.

In this competition, FGVC5 workshop organizers and Malong Technologies challenge you to develop algorithms that will help with an important step towards automatic product recognition – to accurately assign category labels for furniture and home goods images. Individuals/Teams with top submissions will be invited to present their work live at the FGVC5 workshop.

Kaggle is excited to partner with research groups to push forward the frontier of machine learning. Research competitions make use of Kaggle's platform and experience, but are largely organized by the research group's data science team. Any questions or concerns regarding the competition data, quality, or topic will be addressed by them.

Base Inception Resnet V2