US 12,335,477 B2
Neural network feature map quantization method and device
Yongjo Ahn, Seoul (KR); and Jongseok Lee, Seoul (KR)
Assigned to INTELLECTUAL DISCOVERY CO., LTD., Seoul (KR)
Appl. No. 18/253,381
Filed by INTELLECTUAL DISCOVERY CO., LTD., Seoul (KR)
PCT Filed Nov. 18, 2021, PCT No. PCT/KR2021/016998
§ 371(c)(1), (2) Date May 17, 2023,
PCT Pub. No. WO2022/108361, PCT Pub. Date May 27, 2022.
Claims priority of application No. 10-2020-0154765 (KR), filed on Nov. 18, 2020; and application No. 10-2020-0154766 (KR), filed on Nov. 18, 2020.
Prior Publication US 2023/0421764 A1, Dec. 28, 2023
Int. Cl. H04N 19/124 (2014.01); G06V 10/74 (2022.01); G06V 10/764 (2022.01); G06V 10/77 (2022.01); G06V 10/82 (2022.01); H04N 19/136 (2014.01); H04N 19/42 (2014.01)
CPC H04N 19/124 (2014.11) [G06V 10/761 (2022.01); G06V 10/764 (2022.01); G06V 10/7715 (2022.01); G06V 10/82 (2022.01); H04N 19/136 (2014.11); H04N 19/42 (2014.11)] 9 Claims
OG exemplary drawing
 
1. A neural network based video signal processing method, the method comprising:
generating a feature map by using multiple neural networks including a plurality of neural networks; and
performing quantization on the feature map,
wherein the quantization is performed based on an attribute of the feature map or a structure of the multiple neural networks, and
wherein a structure of the multiple neural networks includes at least one of whether the multiple neural networks are connected in series, whether the multiple neural networks are connected in parallel, whether the multiple neural networks are connected in series and in parallel, or a type of a layer adjacent to a current layer that the feature map is generated.