GrokNet
Unified Computer Vision Model Trunk and Embeddings For Commerce.
ecommerce shopping image-search groknet facebook research
Resource links
Top collections
Details
Objectives & Highlights

GrokNet leverages a multi-task learning approach to train a single computer vision trunk. We achieve a 2.1x improvement in exact product match accuracy when compared to the previous state-of-the-art Facebook product recognition system. We achieve this by training on 7 datasets across several commerce verticals, using 80 categorical loss functions and 3 embedding losses

Don't forget to tag @seanbell in your comment.

Authors community post
CEO and Co-Founder, GrokStyle Inc. PhD, Cornell University
Share this project