US 12,406,023 B1
Neural network training method
Jose Manuel Alvarez Lopez, Mountain View, CA (US); Akshay Chawla, Santa Clara, CA (US); Pavlo Molchanov, Mountain View, CA (US); and Hongxu Yin, San Jose, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Jan. 4, 2021, as Appl. No. 17/141,005.
Int. Cl. G06F 18/214 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06V 20/10 (2022.01)
CPC G06F 18/2148 (2023.01) [G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06V 20/10 (2022.01)] 29 Claims
OG exemplary drawing
 
1. A processor, comprising:
one or more circuits to:
use one or more neural networks to identify one or more objects within one or more images and to cause an image of the one or more objects to be generated; and
use one or more second neural networks to detect the one or more objects based, at least in part, on a distance between output of the one or more neural networks and the one or more second neural networks.
 
9. A system, comprising:
one or more processors to:
use one or more neural networks to detect one or more objects within one or more images and to cause an image of the one or more objects to be generated; and
use one or more second neural networks to detect the one or more objects based, at least in part, on a distance between output of the one or more neural networks and the one or more second neural networks.
 
17. A machine-readable medium having stored thereon a set of instructions, which if performed by one or more processors, cause the one or more processors to at least:
use one or more neural networks to detect one or more objects within one or more images and to cause an image of the one or more objects to be generated; and
use one or more second neural networks to detect the one or more objects based, at least in part, on a distance between output of the one or more neural networks and the one or more second neural networks.
 
24. A method, comprising:
training one or more first neural networks to detect one or more objects within one or more images;
using the one or more first neural networks to generate an image of the one or more objects; and
training one or more second neural networks to detect the one or more objects based, at least in part, on a distance between output of the one or more first neural networks and the one or more second neural networks.