US 12,073,608 B2
Learning device, learning method and recording medium
Shuhei Yoshida, Tokyo (JP); and Makoto Terao, Tokyo (JP)
Assigned to NEC CORPORATION, Tokyo (JP)
Appl. No. 17/641,875
Filed by NEC Corporation, Tokyo (JP)
PCT Filed Sep. 27, 2019, PCT No. PCT/JP2019/038343
§ 371(c)(1), (2) Date Mar. 10, 2022,
PCT Pub. No. WO2021/059527, PCT Pub. Date Apr. 1, 2021.
Prior Publication US 2022/0335712 A1, Oct. 20, 2022
Int. Cl. G06K 9/62 (2022.01); G06N 20/00 (2019.01); G06T 7/00 (2017.01); G06V 10/77 (2022.01); G06V 10/776 (2022.01); G06V 10/778 (2022.01)
CPC G06V 10/778 (2022.01) [G06N 20/00 (2019.01); G06T 7/00 (2013.01); G06V 10/77 (2022.01); G06V 10/776 (2022.01)] 7 Claims
OG exemplary drawing
 
1. A learning device for performing learning using a learning dataset,
wherein the learning dataset includes a plurality of partial datasets to which at least a part of all categories of recognition objects is assigned as a responsible range,
wherein all categories of the recognition objects are assigned to one of the plurality of partial datasets,
wherein each of recognition object data included in the partial dataset is given correct answer data indicating any one of the categories belonging to the responsible range of the partial dataset, or indicating that the category of the recognition object does not belong to the responsible range of the partial dataset, and
wherein the learning device comprises:
a memory configured to store instructions; and
one or more processors configured to execute the instructions to:
supply the learning dataset;
output a recognition result for the recognition object data in the supplied learning dataset;
compute an intersection matrix based on the learning dataset;
compute the recognition loss using the recognition result, the intersection matrix, and the correct answer data given to the recognition object data; and
update parameters of the recognition unit based on the recognition loss.