公开(公告)号：US20230368501A1

公开(公告)日：2023-11-16

申请号：US18114177

申请日：2023-02-24

Applicant: NVIDIA Corporation

Inventor： Seonwook Park ,  Shalini De Mello ,  Pavlo Molchanov ,  Umar Iqbal ,  Jan Kautz

IPC: G06V10/772 ,  G06F7/57 ,  G06F17/18 ,  G06N3/088 ,  G06N3/045 ,  G06N3/047 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06V10/772 ,  G06F7/57 ,  G06F17/18 ,  G06N3/088 ,  G06N3/045 ,  G06N3/047 ,  G06V10/774 ,  G06V10/82

Abstract: A neural network is trained to identify one or more features of an image. The neural network is trained using a small number of original images, from which a plurality of additional images are derived. The additional images generated by rotating and decoding embeddings of the image in a latent space generated by an autoencoder. The images generated by the rotation and decoding exhibit changes to a feature that is in proportion to the amount of rotation.

公开(公告)号：US11593661B2

公开(公告)日：2023-02-28

申请号：US16389832

申请日：2019-04-19

Applicant: NVIDIA Corporation

Inventor： Seonwook Park ,  Shalini De Mello ,  Pavlo Molchanov ,  Umar Iqbal ,  Jan Kautz

IPC: G06N3/08 ,  G06F7/57 ,  G06F17/18 ,  G06N3/04 ,  G06N3/088

Abstract: A neural network is trained to identify one or more features of an image. The neural network is trained using a small number of original images, from which a plurality of additional images are derived. The additional images generated by rotating and decoding embeddings of the image in a latent space generated by an autoencoder. The images generated by the rotation and decoding exhibit changes to a feature that is in proportion to the amount of rotation.

公开(公告)号：US20200334543A1

公开(公告)日：2020-10-22

申请号：US16389832

申请日：2019-04-19

Applicant: NVIDIA Corporation

Inventor： Seonwook Park ,  Shalini De Mello ,  Pavlo Molchanov ,  Umar Iqbal ,  Jan Kautz

IPC: G06N3/08 ,  G06F17/18 ,  G06N3/04 ,  G06F7/57

Abstract: A neural network is trained to identify one or more features of an image. The neural network is trained using a small number of original images, from which a plurality of additional images are derived. The additional images generated by rotating and decoding embeddings of the image in a latent space generated by an autoencoder. The images generated by the rotation and decoding exhibit changes to a feature that is in proportion to the amount of rotation.