Invention Grant
- Patent Title: Deep learning model to predict data from an image
-
Application No.: US17306170Application Date: 2021-05-03
-
Publication No.: US12223642B2Publication Date: 2025-02-11
- Inventor: Shreya Sharma , Abhishek Vahadane , Srikanth Ragothaman , Shantanu Majumdar
- Applicant: Rakuten Group, Inc.
- Applicant Address: JP Tokyo
- Assignee: Rakuten Group, Inc.
- Current Assignee: Rakuten Group, Inc.
- Current Assignee Address: JP Tokyo
- Agency: Sughrue Mion, PLLC
- Main IPC: G06T3/40
- IPC: G06T3/40 ; G06N3/08 ; G06T7/00 ; G06T7/73
Abstract:
A method, computer program, and computer system is provided for predicting data from an image. An image is divided into one or more patch images. Spatial features corresponding to the one or more patch images are compressed. Output data corresponding to the compressed spatial features is predicted. The output data is predicted based on minimizing one or more loss functions corresponding to the compressed spatial features.
Public/Granted literature
- US20220351366A1 DEEP LEARNING MODEL TO PREDICT DATA FROM AN IMAGE Public/Granted day:2022-11-03
Information query
