US 12,299,957 B2
Learning apparatus, learning method, and recording medium
Jun Piao, Tokyo (JP)
Assigned to NEC CORPORATION, Tokyo (JP)
Appl. No. 17/792,860
Filed by NEC Corporation, Tokyo (JP)
PCT Filed Jan. 30, 2020, PCT No. PCT/JP2020/003554
§ 371(c)(1), (2) Date Jul. 14, 2022,
PCT Pub. No. WO2021/152801, PCT Pub. Date Aug. 5, 2021.
Prior Publication US 2023/0052101 A1, Feb. 16, 2023
Int. Cl. G06V 10/764 (2022.01); G06T 7/194 (2017.01); G06V 10/774 (2022.01)
CPC G06V 10/764 (2022.01) [G06T 7/194 (2017.01); G06V 10/774 (2022.01); G06V 2201/07 (2022.01)] 7 Claims
OG exemplary drawing
 
1. A learning apparatus comprising:
a memory storing instructions; and
one or more processors configured to execute the instructions to:
acquire image data and label data corresponding to the image data;
extract each object candidate rectangle from the image data;
predict a classification using each object candidate rectangle and output a prediction result;
generate a background object label corresponding to each background object included in the object candidate rectangle as correct answer data corresponding to the object candidate rectangle by using the label data; and
optimize the extracting of each object candidate rectangle and the predicting of the classification by using the prediction result and the correct answer data,
wherein the background object label indicates one of:
(a) a value indicating a degree of an overlap of the object candidate rectangle and the background object;
(b) a rate of an area of the background object included in the object candidate rectangle relative to an area of the object candidate rectangle; and
(c) a rate of an area of the background object included in the object candidate rectangle relative to an area of the background object.