US 12,450,748 B1
Segmentation using an unsupervised neural network training technique
Varun Jampani, Westford, MA (US); Wei-Chih Hung, Merced, CA (US); Sifei Liu, Santa Clara, CA (US); Pavlo Molchanov, Mountain View, CA (US); and Jan Kautz, Lexington, MA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Jul. 18, 2023, as Appl. No. 18/223,348.
Application 18/223,348 is a continuation of application No. 16/378,464, filed on Apr. 8, 2019, granted, now 11,748,887.
Int. Cl. G06V 10/00 (2022.01); G06F 17/15 (2006.01); G06F 18/40 (2023.01); G06N 3/045 (2023.01); G06N 3/047 (2023.01); G06N 3/088 (2023.01); G06T 7/11 (2017.01); G06T 7/143 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/94 (2022.01); G06V 20/40 (2022.01)
CPC G06T 7/11 (2017.01) [G06F 17/15 (2013.01); G06F 18/40 (2023.01); G06N 3/045 (2023.01); G06N 3/047 (2023.01); G06N 3/088 (2013.01); G06T 7/143 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/945 (2022.01); G06V 20/41 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A processor, comprising:
one or more circuits to cause one or more same transformations of one or more objects within one or more images to be applied to one or more corresponding segmentations of the one or more objects to update one or more neural networks based on a set of differentiable loss functions that encode constraints on how to generate one or more segmentations of one or more objects in an image.