August 22, 2020
In this paper, we present GrokNet, a deployed image recognition system for commerce applications. 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. We share our experience of combining diverse sources with wide-ranging label semantics and image statistics, including learning from human annotations, user-generated tags, and noisy search engine interaction data. GrokNet has demonstrated gains in production applications and operates at Facebook scale.
Written by
Sean BellYiqun Liu
Sami Alsheikh
Yina Tang
Ed Pizzi
M. Henning
Karun Singh
Omkar Parkhi
Fedor Borisyuk
Publisher
KDD
March 13, 2021
Model-based Reinforcement Learning (MBRL) is a promising framework for learning control in a data-efficient manner…
Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, Andre Biedenkapp, Kurtland Chua, Frank Hutter, Roberto Calandra
March 13, 2021
February 27, 2021
The use of GPUs has proliferated for machine learning workflows and is now considered mainstream for many deep learning models…
Bilge Acun, Matthew Murphy, Xiaodong Wang, Jade Nie, Carole-Jean Wu, Kim Hazelwood
February 27, 2021
February 01, 2021
Inference in deep neural networks can be computationally expensive, and networks capable of anytime inference are important in scenarios where the amount of compute or quantity of input data varies over time.…
Adria Ruiz, Jakob Verbeek
February 01, 2021
January 09, 2021
Super-resolution aims at increasing the resolution and level of detail within an image.…
Baptiste Roziere, Nathanaël Carraz Rakotonirina, Vlad Hosu, Andry Rasoanaivo, Hanhe Lin, Camille Couprie, Olivier Teytaud
January 09, 2021