OBJECT DETECTION WITH CROSS-DOMAIN MIXING

Implementations are described herein for improving unsupervised domain adaptation (UDA) by using improved adaptive teacher for object detection with cross-domain mix-up. In various implementations, cross-domain training of an object detection machine learning model may include: performing weak augme...

Full description

Saved in:
Bibliographic Details
Main Authors Ngai, Alexander, Vu, Minh Thanh, Yuan, Bodi, Sun, Baochen, Li, Yueqi
Format Patent
LanguageEnglish
Published 16.05.2024
Subjects
CALCULATING
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Implementations are described herein for improving unsupervised domain adaptation (UDA) by using improved adaptive teacher for object detection with cross-domain mix-up. In various implementations, cross-domain training of an object detection machine learning model may include: performing weak augmentation on images from a target domain DT to generate a first set of weakly augmented target domain images; perform strong augmentation on images from the source domain DS and images from the target domain DT to generate a second set of strongly augmented images; processing the second set of strongly augmented images to generate a third set of inter-domain mixes of the images from DS and DT; and jointly train the object detection machine learning model, as a student machine learning model, with a teacher machine learning model using the first and third sets.
Bibliography:Application Number: US202318388773