Invention Grant
- Patent Title: Computationally efficient unsupervised DNN pretraining
-
Application No.: US17817704Application Date: 2022-08-05
-
Publication No.: US12175732B2Publication Date: 2024-12-24
- Inventor: Siddhartha Gupta , Wei Tong , Upali P. Mudalige
- Applicant: GM Global Technology Operations LLC
- Applicant Address: US MI Detroit
- Assignee: GM Global Technology Operations LLC
- Current Assignee: GM Global Technology Operations LLC
- Current Assignee Address: US MI Detroit
- Agency: Vivacqua Crane, PLLC
- Main IPC: G06V10/778
- IPC: G06V10/778 ; G06T7/11 ; G06V10/25 ; G06V10/26 ; G06V10/74 ; G06V10/774

Abstract:
A system comprises a computer including a processor and a memory. The memory includes instructions such that the processor is programmed to determine a pairwise region of interest feature similarity based on features extracted from a first cropped image portion and corresponding point cloud data and features extracted from a second cropped image portion and corresponding point cloud data. The processor is also programmed to determine a loss using a loss function based on the pairwise region of interest feature similarity, wherein the loss function corresponds to at least one a first deep neural network or a second deep neural network. The processor is also programmed to update at least one weight of the at least one of the first deep neural network or the second deep neural network based on the loss.
Public/Granted literature
- US20240046627A1 COMPUTATIONALLY EFFICIENT UNSUPERVISED DNN PRETRAINING Public/Granted day:2024-02-08
Information query