• Home
  • Search
  • Domain adaptation for applications in computer vision with limited data
  • https://doi.org/10.63028/10067/2122260151162165141Copy DOI Icon

Domain adaptation for applications in computer vision with limited data

  • Jan 1, 2024
  • Mattias Billast
Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

This dissertation explores the challenges and solutions of using domain adaptation in real-time computer vision applications with limited labeled data. Computer vision, initially based on traditional feature extraction methods, has progressed significantly with deep learning, achieving breakthroughs in areas like image classification and object detection. However, deep learning models often require large labeled datasets, which can be expensive and time-consuming to obtain, especially for custom applications. Domain adaptation offers a way to tackle this problem by using external data sources to improve model performance in a target domain. Its effectiveness depends on the domain gap—if the gap between source and target data is too large, adaptation becomes difficult. The dissertation focuses on two applications: maritime autonomous navigation and human motion prediction. In maritime navigation, the goal is to detect, track, and locate obstacles for autonomous vessels, but a lack of labeled data poses a challenge. By using domain adaptation techniques, data from external sources (such as public object detection datasets) is leveraged to improve model accuracy. The second application involves predicting the physical and cognitive ergonomics of operators performing repetitive tasks. This is done by analyzing human pose data and anticipating movements to prevent musculoskeletal issues. Data from a VR setup helps train the model, with domain adaptation used to improve its performance despite limited labeled data. Both applications require real-time performance with lightweight models. Domain adaptation techniques are used to enhance the models by incorporating external data, like maritime object detection datasets or VR controller data for human pose prediction. Overall, the thesis highlights the importance of domain adaptation in improving model accuracy with limited data, showing that external data sources can significantly enhance real-time computer vision applications, both in real-world and academic settings. The key contribution is that domain adaptation can utilize any useful external data to improve performance.

Similar Papers
  • Conference Article
  • Citations3

DATA++: An Automated Tool for Intelligent Data Augmentation Using Wikidata

  • Jul 01, 2019
  • Waran Taveekarn +5
  • Conference Article
  • Citations8

Learning Target Predictive Function without Target Labels

  • Dec 01, 2012
  • Chun-Wei Seah +3
  • Research Article
  • Citations4

Deep learning-based domain adaptation for a generalized detection of wear phenomena during blanking

  • Aug 01, 2023
  • Manufacturing Letters
  • Christian Kubik +3
  • PDF
  • Research Article
  • Citations5

Kurcuma: a kitchen utensil recognition collection for unsupervised domain adaptation

  • Feb 17, 2023
  • Pattern Analysis and Applications
  • Adrian Rosello +4
  • Conference Article
  • Citations1

Data-Importance-Aware Waterfilling for Adaptive Real-Time Communication in Computer Vision Applications

  • Jun 08, 2025
  • Chunmei Xu +2
  • PDF
  • Research Article
  • Citations11

Seeding innovation: the role of internal and external digital data in agri-food product innovation

  • May 14, 2024
  • British Food Journal
  • Moreno Frau +1
  • Book Chapter

Data Mining Process: Creation of the Analytical File with External Data Sources

  • Jan 01, 2014
  • Richard Boire
  • PDF
  • Research Article
  • Citations1

Correlation enhanced distribution adaptation for prediction of fall risk

  • Feb 12, 2024
  • Scientific Reports
  • Ziqi Guo +4
  • Research Article
  • Citations3

Effective Entity Augmentation by Querying External Data Sources

  • Jul 01, 2023
  • Proceedings of the VLDB Endowment
  • Christopher Buss +5
  • Conference Article
  • Citations14

Achieving adaptivity for OLAP-XML federations

  • Nov 07, 2003
  • Dennis Pedersen +1
  • PDF
  • Research Article
  • Citations12

ORCID coverage in research institutions—Readiness for partially automated research reporting

  • Nov 10, 2022
  • Frontiers in Research Metrics and Analytics
  • Kathrin Schnieders +6
  • Research Article
  • Citations10

Using item response theory to develop a shortened practice environment scale of the nursing work index.

  • May 30, 2023
  • Research in Nursing & Health
  • Aoyjai P Montgomery +4
  • Research Article
  • Citations5

Predicting Adherence to Computer-Based Cognitive Training Programs Among Older Adults: Study of Domain Adaptation and Deep Learning

  • Sep 16, 2024
  • JMIR Aging
  • Ankita Singh +8
  • Research Article
  • Citations360

Domain Adaptation Techniques for EEG-Based Emotion Recognition: A Comparative Study on Two Public Datasets

  • Mar 01, 2019
  • IEEE Transactions on Cognitive and Developmental Systems
  • Zirui Lan +4
  • Research Article
  • Citations4

Distributionally robust unsupervised domain adaptation

  • Jun 07, 2023
  • Journal of Computational and Applied Mathematics
  • Yibin Wang +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.