US 12,380,738 B1
System to determine compact representation of data
Manoj Aggarwal, Seattle, WA (US); Gerard Guy Medioni, Los Angeles, CA (US); Lavisha Aggarwal, Seattle, WA (US); Prithviraj Banerjee, Redmond, WA (US); Jiuhong Xiao, Long Island, NY (US); Rajeev Ranjan, Seattle, WA (US); and Dilip Kumar, Seattle, WA (US)
Assigned to AMAZON TECHNOLOGIES, INC., Seattle, WA (US)
Filed by AMAZON TECHNOLOGIES, INC., Seattle, WA (US)
Filed on Dec. 2, 2021, as Appl. No. 17/457,302.
Int. Cl. G06V 40/50 (2022.01); G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06T 9/00 (2006.01); G06V 40/10 (2022.01)
CPC G06V 40/50 (2022.01) [G06F 18/214 (2023.01); G06F 18/22 (2023.01); G06T 9/00 (2013.01); G06V 40/11 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
accessing training input data comprising image data;
training an encoder module to produce a compact representation of the image data using the training input data and a loss function comprising:
a bitrate loss,
a distortion loss, and
an embedding loss; and
storing weight data associated with training the encoder module.