“Powered by AI: Advancing Product Understanding and Building New Shopping Experiences”, Tamara Berg, Sean Bell, Manohar Paluri, Andrei Chtcherbatchenko, Harry Chen, Francis Ge, Bo Yin2020-05-19 (; similar)⁠:

Today we’re announcing:

…We built, trained, and deployed a model with 83 loss functions across seven data sets to combine multiple verticals into a single embedding space. This universal model allows us to leverage many more sources of information, which increases our accuracy and outperforms our single vertical-focused models…In the GrokNet training architecture, a major challenge is managing 7 datasets and 83 loss functions, so that they all perform well simultaneously. To solve this, we adjust the batch sizes and loss weights, using more images per batch and higher loss weights for the challenging tasks. We also use weakly supervised learning to automatically generate additional training data, further improving accuracy.

…Our long-term vision is to build an all-in-one AI lifestyle assistant that can accurately search and rank billions of products, while personalizing to individual tastes. That same system would make online shopping just as social as shopping with friends in real life. Going one step further, it would advance visual search to make your real-world environment shoppable. If you see something you like (clothing, furniture, electronics, etc.), you could snap a photo of it and the system would find that exact item, as well as several similar ones to purchase right then and there…While these systems are fragmented right now, incorporating everything into one system is the ambitious challenge we’ve set out to achieve. Building these systems across all Facebook platforms would enable shoppers to connect with their friends and family to get an opinion on an automatically generated 360-degree 3D view of an item. These friends can weigh in on which sneakers they like most or which size painting looks best in the shopper’s kitchen. By combining state-of-the-art computer vision with advancements in other AI domains, such as language understanding, personalization, and social-first experiences, we’re well positioned to transform online shopping for everyone.