US 12,456,055 B2
Weakly-supervised object detection using one or more neural networks
Zhiding Yu, Santa Clara, CA (US); Zhongheng Ren, Davis, CA (US); Xiaodong Yang, Fremont, CA (US); Ming-Yu Liu, San Jose, 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 Jun. 17, 2019, as Appl. No. 16/443,346.
Prior Publication US 2020/0394458 A1, Dec. 17, 2020
Int. Cl. G06K 9/62 (2022.01); G06F 18/21 (2023.01); G06F 18/2113 (2023.01); G06F 18/214 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06N 3/084 (2023.01); G06V 10/25 (2022.01); G06V 10/44 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 20/10 (2022.01)
CPC G06N 3/084 (2013.01) [G06F 18/2113 (2023.01); G06F 18/214 (2023.01); G06F 18/217 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06V 10/25 (2022.01); G06V 10/454 (2022.01); G06V 10/7753 (2022.01); G06V 10/82 (2022.01); G06V 20/10 (2022.01)] 30 Claims
OG exemplary drawing
 
1. One or more processors, comprising:
circuitry to use one or more neural networks to generate one or more labels of one or more objects within one or more images based, at least in part, on:
one or more indications where the one or more objects are likely to appear in the one or more images;
a region of interest (ROI) score generated for a set of objects proposals; and
an indication of the number of the one or more objects corresponding to the one or more labels based on the ROI score of the set of the object proposals.