US 12,367,683 B2
Efficient construction and consumption of auxiliary channels in convolutional neural networks
Amin Ansari, Kirkland, WA (US); Sai Madhuraj Jadhav, San Diego, CA (US); and Yunxiao Shi, San Diego, CA (US)
Assigned to QUALCOMM Incorporated, San Diego, CA (US)
Filed by QUALCOMM Incorporated, San Diego, CA (US)
Filed on Sep. 7, 2023, as Appl. No. 18/463,040.
Claims priority of provisional application 63/500,414, filed on May 5, 2023.
Prior Publication US 2024/0371169 A1, Nov. 7, 2024
Int. Cl. G06V 20/56 (2022.01); G05D 1/00 (2006.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06V 10/82 (2022.01)
CPC G06V 20/56 (2022.01) [G05D 1/021 (2013.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06V 10/82 (2022.01); G06T 2207/10024 (2013.01); G06T 2207/30252 (2013.01)] 33 Claims
OG exemplary drawing
 
1. A method of processing image data, the method comprising:
obtaining an image to be processed;
obtaining a first auxiliary value for the image and a second auxiliary value for the image;
generating an input component including the first auxiliary value and the second auxiliary value arranged in a pattern according to a stride of a neural network; and
providing the image and the input component to the neural network.