	US 12,236,349 B2
	Guided training of machine learning models with convolution layer feature data fusion
Shubhankar Mange Borse, San Diego, CA (US); Nojun Kwak, San Diego, CA (US); Daniel Hendricus Franciscus Dijkman, Haarlem (NL); and Bence Major, Amsterdam (NL)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Nov. 13, 2020, as Appl. No. 17/098,159.
Claims priority of provisional application 62/935,428, filed on Nov. 14, 2019.
Prior Publication US 2021/0150347 A1, May 20, 2021
Int. Cl. G06N 3/084 (2023.01); G06F 18/2137 (2023.01); G06F 18/25 (2023.01); G06N 3/048 (2023.01); G06N 3/063 (2023.01); G06N 3/08 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)

CPC G06N 3/084 (2013.01) [G06F 18/2137 (2023.01); G06F 18/251 (2023.01); G06N 3/048 (2023.01); G06N 3/063 (2013.01); G06N 3/08 (2013.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)]

26 Claims

1. A method, comprising:

receiving a primary domain feature map from a first layer of a neural network model;

receiving supplementary domain feature data;

generating a supplementary domain feature map based on scaled supplementary domain feature data, wherein the supplementary domain feature map is normalized based on supplementary domain feature scaling data, and a fully connected layer of the neural network model is configured to scale the supplementary domain feature data from a first dimensionality to a second dimensionality associated with an output of a pooling layer of the neural network model;

fusing the supplementary domain feature map with the primary domain feature map to generate a fused feature map; and

providing the fused feature map to a second layer of the neural network model.