Title:
METHOD AND DEVICE FOR COMPRESSING FEATURE TENSOR ON BASIS OF NEURAL NETWORK
Document Type and Number:
WIPO Patent Application WO/2023/177272
Kind Code:
A1
Abstract:
A method and a device for processing an image on the basis of a neural network, according to an embodiment of the present invention, can acquire a feature tensor from an input image by using a first neural network including a plurality of neural network layers, acquire a quantized feature tensor by quantizing the acquired feature tensor on the basis of the quantization size, and generate a bitstream by performing entropy encoding on the quantized feature tensor.
Inventors:
AHN YONGJO (KR)
LEE JONGSEOK (KR)
LEE JONGSEOK (KR)
Application Number:
PCT/KR2023/003661
Publication Date:
September 21, 2023
Filing Date:
March 20, 2023
Export Citation:
Assignee:
INTELLECTUAL DISCOVERY CO LTD (KR)
International Classes:
H04N19/124; G06N3/08; G06T9/00; H04N19/13; H04N19/146; H04N19/176; H04N19/18; H04N19/184; H04N19/60
Foreign References:
US10909728B1 | 2021-02-02 | |||
KR20210011461A | 2021-02-01 | |||
KR20210108413A | 2021-09-02 | |||
KR20200064811A | 2020-06-08 | |||
KR20210156538A | 2021-12-27 |
Attorney, Agent or Firm:
CHOE, Yun Seo (KR)
Download PDF:
Previous Patent: ORGANIC ELECTROLUMINESCENT DEVICE
Next Patent: LENS ASSEMBLY AND ELECTRONIC DEVICE COMPRISING SAME
Next Patent: LENS ASSEMBLY AND ELECTRONIC DEVICE COMPRISING SAME