公开(公告)号：US20230290132A1

公开(公告)日：2023-09-14

申请号：US18007288

申请日：2021-07-28

Applicant: Magic Leap, Inc.

Inventor： Siddharth MAHENDRAN ,  Nitin BANSAL ,  Nitesh SEKHAR ,  Manushree GANGWAR ,  Khushi GUPTA ,  Prateek SINGHAL ,  Tarrence VAN AS ,  Adithya Shricharan Srinivasa RAO

IPC: G06V10/82 ,  G06V10/764

CPC classification number: G06V10/82 ,  G06V10/764

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an object recognition neural network using multiple data sources. One of the methods includes receiving training data that includes a plurality of training images from a first source and images from a second source. A set of training images are obtained from the training data. For each training image in the set of training images, contrast equalization is applied to the training image to generate a modified image. The modified image is processed using the neural network to generate an object recognition output for the modified image. A loss is determined based on errors between, for each training image in the set, the object recognition output for the modified image generated from the training image and ground-truth annotation for the training image. Parameters of the neural network are updated based on the determined loss.