MODEL-AWARE SYNTHETIC IMAGE GENERATION

A computer implemented method includes obtaining a first deep neural network (DNN) model trained on labeled real image data for a downstream vision task, obtaining a second DNN model trained on synthetic images created with random image parameter values for the downstream vision task, obtaining a th...

Full description

Saved in:
Bibliographic Details
Main Authors WANG, Di, LYMPEROPOULOS, Dimitrios, SHALEV, Emanuel, PEKELNY, Yuri, URBINA ESCOS, Pedro
Format Patent
LanguageEnglish
French
German
Published 01.06.2022
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:A computer implemented method includes obtaining a first deep neural network (DNN) model trained on labeled real image data for a downstream vision task, obtaining a second DNN model trained on synthetic images created with random image parameter values for the downstream vision task, obtaining a third DNN model trained on the labeled real image data and the synthetic images for the downstream vision task, performing a forward pass execution of each model to generate a loss, backpropagating the loss to modify parameter values, and iterating the forward pass execution and backpropagating with images generated by the modified parameters to jointly train the models and optimize the parameters.
Bibliography:Application Number: EP20200736523