Invention Grant
- Patent Title: Multi-task self-training for learning general representations
-
Application No.: US17697750Application Date: 2022-03-17
-
Publication No.: US12080055B2Publication Date: 2024-09-03
- Inventor: Tsung-Yi Lin , Barret Zoph , Ekin Dogus Cubuk , Golnaz Ghiasi , Quoc V. Le
- Applicant: Google LLC
- Applicant Address: US CA Mountain View
- Assignee: Google LLC
- Current Assignee: Google LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06V10/82
- IPC: G06V10/82 ; G06N3/084 ; G06V10/764 ; G06V10/77 ; G06V10/774 ; G06V10/776 ; G06V10/80
Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an image representation neural network.
Public/Granted literature
- US20220301298A1 MULTI-TASK SELF-TRAINING FOR LEARNING GENERAL REPRESENTATIONS Public/Granted day:2022-09-22
Information query
