Invention Grant
- Patent Title: Neural networks for coarse- and fine-object classifications
-
Application No.: US17836287Application Date: 2022-06-09
-
Publication No.: US11842282B2Publication Date: 2023-12-12
- Inventor: Junhua Mao , Congcong Li , Yang Song
- Applicant: Waymo LLC
- Applicant Address: US CA Mountain View
- Assignee: Waymo LLC
- Current Assignee: Waymo LLC
- Current Assignee Address: US CA Mountain View
- Agency: Fish & Richardson P.C.
- Main IPC: G06V20/56
- IPC: G06V20/56 ; G06N3/084 ; G05D1/02 ; G06N3/08 ; G06F18/20 ; G06F18/25 ; G06F18/21 ; G06F18/214 ; G06F18/2431 ; G06N3/044 ; G06V30/19 ; G06V30/24 ; G06V10/764 ; G06V10/80 ; G06V10/82 ; G06V20/58

Abstract:
Aspects of the subject matter disclosed herein include methods, systems, and other techniques for training, in a first phase, an object classifier neural network with a first set of training data, the first set of training data including a first plurality of training examples, each training example in the first set of training data being labeled with a coarse-object classification; and training, in a second phase after completion of the first phase, the object classifier neural network with a second set of training data, the second set of training data including a second plurality of training examples, each training example in the second set of training data being labeled with a fine-object classification.
Public/Granted literature
- US20220374650A1 NEURAL NETWORKS FOR COARSE- AND FINE-OBJECT CLASSIFICATIONS Public/Granted day:2022-11-24
Information query