Conditional patch-based domain randomization: improving texture domain randomization using natural image patches

Mohammad Ani*, Hector Basevi, Ales Leonardis

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

26 Downloads (Pure)

Abstract

Using Domain Randomized synthetic data for training deep learning systems is a promising approach for addressing the data and the labeling requirements for supervised techniques to bridge the gap between simulation and the real world. We propose a novel approach for generating and applying class-specific Domain Randomization textures by using randomly cropped image patches from real-world data. In evaluation against the current Domain Randomization texture application techniques, our approach outperforms the highest performing technique by 4.94 AP and 6.71 AP when solving object detection and semantic segmentation tasks on the YCB-M real-world robotics dataset. Our approach is a fast and inexpensive way of generating Domain Randomized textures while avoiding the need to handcraft texture distributions currently being used.
Original languageEnglish
Title of host publication2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Place of PublicationKyoto, Japan
PublisherIEEE
Pages1979-1985
ISBN (Electronic)978-1-6654-7927-1
ISBN (Print)978-1-6654-7928-8
DOIs
Publication statusPublished - 26 Dec 2022
Event2022 IEEE/RSJ International Conference on Intelligent Robots and Systems - Kyoto, Japan
Duration: 23 Oct 202227 Oct 2022
https://iros2022.org/

Publication series

NameProceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherIEEE
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Conference

Conference2022 IEEE/RSJ International Conference on Intelligent Robots and Systems
Abbreviated titleIROS 2022
Country/TerritoryJapan
CityKyoto
Period23/10/2227/10/22
Internet address

Bibliographical note

Not yet published as of 20/01/2023

Keywords

  • Domain randomisation
  • Computer vision
  • Synthetic data

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Conditional patch-based domain randomization: improving texture domain randomization using natural image patches'. Together they form a unique fingerprint.

Cite this