Invention Grant
- Patent Title: Methods and system for training and reinforcing computer vision models using distributed computing
-
Application No.: US16944737Application Date: 2020-07-31
-
Publication No.: US11463517B2Publication Date: 2022-10-04
- Inventor: Rohit Shirish Saraf , Bhumip Khasnabish , John Aceron
- Applicant: Verizon Patent and Licensing Inc.
- Applicant Address: US NJ Basking Ridge
- Assignee: Verizon Patent and Licensing Inc.
- Current Assignee: Verizon Patent and Licensing Inc.
- Current Assignee Address: US NJ Basking Ridge
- Main IPC: H04L67/1095
- IPC: H04L67/1095 ; G06N3/08 ; G06K9/62 ; G06N3/04 ; H04L67/00

Abstract:
Systems and methods described herein perform computer vision (CV) model training in a distributed edge network. Regional Multi-access Edge Compute (MEC) clusters are provided with a local copy of a CV model and a local synthetic training data generator. A MEC cluster receives client data requiring computer vision and applies the local copy of the CV model to the client data. The MEC cluster detects an exception to the local copy of the CV model and generates local synthetic training data for the exception. The MEC cluster updates, based on the local synthetic training data, the local copy of the CV model to form an updated local CV model. The MEC cluster sends the local synthetic training data and the updated local CV model to a central network. The central network uses the local synthetic training data to update a master CV model and any other interconnected CV models.
Public/Granted literature
- US20220038534A1 METHODS AND SYSTEM FOR TRAINING AND REINFORCING COMPUTER VISION MODELS USING DISTRIBUTED COMPUTING Public/Granted day:2022-02-03
Information query