US 11,727,280 B2
Generative neural network distillation
Sergey Tulyakov, Marina del Rey, CA (US); Sergei Korolev, Marina del Rey, CA (US); Aleksei Stoliar, Marina del Rey, CA (US); Maksim Gusarov, Marina del Rey, CA (US); Sergei Kotcur, Los Angeles, CA (US); Christopher Yale Crutchfield, San Diego, CA (US); and Andrew Wan, Marina del Rey, CA (US)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on Mar. 2, 2021, as Appl. No. 17/189,563.
Application 17/189,563 is a continuation of application No. 16/119,956, filed on Aug. 31, 2018, granted, now 10,963,748.
Prior Publication US 2021/0182624 A1, Jun. 17, 2021
Int. Cl. G06N 3/088 (2023.01); G06N 3/08 (2023.01); G06F 18/21 (2023.01); G06F 18/214 (2023.01); G06N 3/045 (2023.01); G06V 10/764 (2022.01); G06V 10/774 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01)
CPC G06N 3/088 (2013.01) [G06F 18/2148 (2023.01); G06F 18/2185 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06V 10/764 (2022.01); G06V 10/7747 (2022.01); G06V 10/7788 (2022.01); G06V 10/82 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
identifying, using a plurality of first neural networks, an object in an image, wherein each of the plurality of first neural networks is trained to recognize one object of a plurality of objects;
selecting a second neural network trained to apply an effect to images that comprise the identified object; and
generating a result image by using the second neural network to apply the effect to the image, wherein the plurality of second neural networks are trained on input data and output data generated by a teacher generative neural network using adversarial loss.