ALGORITHM AND METHOD FOR DYNAMICALLY VARYING QUANTIZATION PRECISION OF DEEP LEARNING NETWORK

An image recognition method includes the steps of: for a deep learning network that carries out object recognition on a random image, carrying out quantization corresponding to the number of a plurality of different bits to generate a plurality of quantization models respectively corresponding to th...

Full description

Saved in:
Bibliographic Details
Main Authors LIM, Kyeong Jong, LEE, Hyuk Jae, RYU, Soo Jung, YOO, Ook Sang, CHON, Ji Yea
Format Patent
LanguageEnglish
Published 22.02.2024
Subjects
CALCULATING
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:An image recognition method includes the steps of: for a deep learning network that carries out object recognition on a random image, carrying out quantization corresponding to the number of a plurality of different bits to generate a plurality of quantization models respectively corresponding to the number of bits; receiving image data as an input for the deep learning network; determining the uncertainty of the input image data; selecting any one of the plurality of quantization models on the basis of the determined uncertainty; and recognizing an object from the image data by using the selected quantization model, and outputting, as the result of the object recognition, a label corresponding to the image data.
Bibliography:Application Number: US202018270638