Training of Deep Learning Models Using Synthetic Datasets - Publication - Bridge of Knowledge

Your account

login

Search

Training of Deep Learning Models Using Synthetic Datasets

Abstract

In order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning models for object detection and instance segmentation without being involved in the generation of real world datasets. In principle, we generate and annotate images with open-source software and 3D models that mimic real life objects. This approach allows us significantly reduce the effort required to gather pictures as well as automatize data tagging. It is worth noting that such synthetic datasets can be easily manipulated, e.g. to reduce the texture bias that often occurs in the resulting trained convolutional networks. Using the Mask R-CNN instance segmentation model as an example, we demonstrate that a network trained on the synthetic dataset of kitchen facilities shows remarkable performance on the validation dataset of real-world human-annotated photos. We show that our approach helps to bridge the domain gap between pre-trained models and their specific applications. In summary, such synthetic datasets help overcome the problem of acquiring and tagging thousands of images, while reducing the time and labor costs associated with the preparation of an appropriate real dataset

Citations

  • 3

    CrossRef

  • 0

    Web of Science

  • 4

    Scopus

Authors (2)

Cite as

Full text

full text is not available in portal

Keywords

Details

Category:
Monographic publication
Type:
rozdział, artykuł w książce - dziele zbiorowym /podręczniku w języku o zasięgu międzynarodowym
Title of issue:
Intelligent and Safe Computer Systems in Control and Diagnostics strony 141 - 152
Language:
English
Publication year:
2022
Bibliographic description:
Kowalczuk Z., Glinko J.: Training of Deep Learning Models Using Synthetic Datasets// Intelligent and Safe Computer Systems in Control and Diagnostics/ : , 2023, s.141-152
DOI:
Digital Object Identifier (open in new tab) 10.1007/978-3-031-16159-9_12
Verified by:
Gdańsk University of Technology

seen 84 times

Recommended for you

Instance segmentation of stack composed of unknown objects

2023

Breast MRI segmentation by deep learning: key gaps and challenges

2023

Deep CNN based decision support system for detection and assessing the stage of diabetic retinopathy

2018

Using Isolation Forest and Alternative Data Products to Overcome Ground Truth Data Scarcity for Improved Deep Learning-based Agricultural Land Use Classification Models

  • A. Pereira García,
  • L. Porwol,
  • A. Ojo
2023
Meta Tags