US 11,854,241 B2
Method and apparatus with dilated convolution
Junwoo Jang, Seoul (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Apr. 28, 2021, as Appl. No. 17/243,057.
Application 17/243,057 is a continuation of application No. 16/393,107, filed on Apr. 24, 2019, granted, now 11,017,264.
Claims priority of application No. 10-2018-0153723 (KR), filed on Dec. 3, 2018.
Prior Publication US 2021/0248413 A1, Aug. 12, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/10 (2017.01); G06V 10/44 (2022.01); G06N 3/08 (2023.01); G06F 18/213 (2023.01); G06F 18/2413 (2023.01); G06V 30/19 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/454 (2022.01) [G06F 18/213 (2023.01); G06F 18/2413 (2023.01); G06N 3/08 (2013.01); G06V 10/82 (2022.01); G06V 30/19173 (2022.01)] 22 Claims
OG exemplary drawing
 
1. A neural network apparatus, comprising:
one or more processors configured to:
acquire an input feature map and trained weights corresponding to non-dilated weights,
generate a plurality of sub-feature maps by applying a dilation rate on the input feature map, including splitting the input feature map based on the dilation rate,
generate a plurality of intermediate feature maps by performing a convolution operation between the plurality of sub-feature maps and the trained weights, and
generate a dilated output feature map by merging the plurality of intermediate feature maps based on the dilation rate.