Patents Assigned to INDUSTRY-UNIVERSITY COOPERATION FOUNDATION KOAEA AEROSPACE UNIVERSITY
  • METHOD AND DEVICE FOR ENCODING/DECODING DEEP NEURAL NETWORK MODEL
    Publication number: 20230008124
    Abstract: Disclosed herein are a method and apparatus for encoding/decoding a deep neural network. According to the present disclosure, the method for decoding a deep neural network may include: in a plurality of layers of the deep neural network, entropy decoding quantization information for a current layer; performing dequantization on the current layer; and obtaining a plurality of layers of the deep neural network. At least one of global quantization and local quantization is performed on the current layer.
    Type: Application
    Filed: December 11, 2020
    Publication date: January 12, 2023
    Applicants: Korea Electronics Technology Institute, INDUSTRY-UNIVERSITY COOPERATION FOUNDATION KOAEA AEROSPACE UNIVERSITY
    Inventors: Byeong Ho CHOI, Sang Seol LEE, Sung Joon JANG, Sung Jei KIM, Jae Gon KIM, Hyeon Cheol MOON