US 12,175,732 B2
Computationally efficient unsupervised DNN pretraining
Siddhartha Gupta, Rochester Hills, MI (US); Wei Tong, Troy, MI (US); and Upali P. Mudalige, Rochester Hills, MI (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Aug. 5, 2022, as Appl. No. 17/817,704.
Prior Publication US 2024/0046627 A1, Feb. 8, 2024
Int. Cl. G06V 10/778 (2022.01); G06T 7/11 (2017.01); G06V 10/25 (2022.01); G06V 10/26 (2022.01); G06V 10/74 (2022.01); G06V 10/774 (2022.01)
CPC G06V 10/778 (2022.01) [G06T 7/11 (2017.01); G06V 10/25 (2022.01); G06V 10/26 (2022.01); G06V 10/761 (2022.01); G06V 10/774 (2022.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20132 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system comprising a computer including a processor and a memory, the memory including 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;
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; and
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.