公开(公告)号：US11663476B2

公开(公告)日：2023-05-30

申请号：US16772557

申请日：2018-12-13

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung-Hyun Cho ,  Youn-Hee Kim ,  Jin-Wuk Seok ,  Joo-Young Lee ,  Woong Lim ,  Jong-Ho Kim ,  Dae-Yeol Lee ,  Se-Yoon Jeong ,  Hui-Yong Kim ,  Jin-Soo Choi ,  Je-Won Kang

IPC: G06V10/75 ,  G06N3/08 ,  G06N3/04 ,  G06V10/82 ,  G06F18/214

CPC classification number: G06V10/751 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06V10/82

Abstract: Disclosed herein are a method and apparatus for compressing learning parameters for training of a deep-learning model and transmitting the compressed parameters in a distributed processing environment. Multiple electronic devices in the distributed processing system perform training of a neural network. By performing training, parameters are updated. The electronic device may share the updated parameter thereof with additional electronic devices. In order to efficiently share the parameter, the residual of the parameter is provided to the additional electronic devices. When the residual of the parameter is provided, the additional electronic devices update the parameter using the residual of the parameter.

公开(公告)号：US11019355B2

公开(公告)日：2021-05-25

申请号：US16374601

申请日：2019-04-03

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seung-Hyun Cho ,  Je-Won Kang ,  Na-Young Kim ,  Jung-Kyung Lee ,  Joo-Young Lee ,  Hyunsuk Ko ,  Youn-Hee Kim ,  Jong-Ho Kim ,  Jin-Wuk Seok ,  Dae-Yeol Lee ,  Woong Lim ,  Se-Yoon Jeong ,  Hui-Yong Kim ,  Jin-Soo Choi

IPC: H04N19/513 ,  G06N20/00 ,  H04N19/132 ,  H04N19/105

Abstract: An inter-prediction method and apparatus uses a reference frame generated based on deep learning. In the inter-prediction method and apparatus, a reference frame is selected, and a virtual reference frame is generated based on the selected reference frame. A reference picture list is configured to include the generated virtual reference frame, and inter prediction for a target block is performed based on the virtual reference frame. The virtual reference frame may be generated based on a deep-learning network architecture, and may be generated based on video interpolation and/or video extrapolation that use the selected reference frame.