• Home
  • Search
  • Class-wise histogram matching-based domain adaptation in deep learning-based bridge element segmentation
  • Cite Icon4
  • https://doi.org/10.1007/s13349-025-00922-0Copy DOI Icon

Class-wise histogram matching-based domain adaptation in deep learning-based bridge element segmentation

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This study focused on the problem of domain shift in deep learning-based bridge element segmentation. The impracticability of accounting for all possible variabilities vis-à-vis structural shape, size, color, texture, illumination, and other operational conditions in the training process leads to the deterioration in the model performance when applied to test data from novel unseen domains. In such situations, rebuilding the model with labeled training data from the target domain becomes prohibitively expensive and time-consuming in many practical cases. Recent advancements in unsupervised domain adaptation techniques are known to provide viable solutions to this problem. However, it was observed in this study that the performance gain afforded by the domain adaptation techniques is not significant enough to adequately close the domain gaps commonly encountered in vision-based robotic bridge inspections. This study, therefore, proposed a class-wise histogram matching-based data augmentation technique that seeks to complement the domain adaptation strategy, leading to a significantly improved adaptation in situations where no labeled data are available from the target domain. The proposed framework is validated with two case studies concerning deep learning-based bridge element segmentation in inspection images collected by unmanned aerial vehicles (UAVs). It produced a mean intersection-over-union which is 21.2% and 21.3% higher than a benchmark domain adaptation method. In the future, this study can be extended to other relevant application areas, including but not limited to autonomous vision-based bridge defect detection and post-disaster structural reconnaissance.

Loading PDF

Similar Papers
  • Book Chapter
  • Citations3

Harmonised Segmentation of Neonatal Brain MRI: A Domain Adaptation Approach

  • Jan 01, 2020
  • Irina Grigorescu +6
  • Conference Article
  • Citations8

Learning Target Predictive Function without Target Labels

  • Dec 01, 2012
  • Chun-Wei Seah +3
  • Research Article
  • Citations37

Unsupervised Adversarial Domain Adaptation Network for Semantic Segmentation

  • Dec 26, 2019
  • IEEE Geoscience and Remote Sensing Letters
  • Wei Liu +1
  • Research Article
  • Citations4

Distributionally robust unsupervised domain adaptation

  • Jun 07, 2023
  • Journal of Computational and Applied Mathematics
  • Yibin Wang +1
  • 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
  • Research Article
  • Citations6

Cluster-based adaptive SVM: A latent subdomains discovery method for domain adaptation problems

  • Jun 10, 2017
  • Computer Vision and Image Understanding
  • Azadeh Sadat Mozafari +1
  • PDF
  • Research Article
  • Citations33

Domain Adversarial Neural Networks for Large-Scale Land Cover Classification

  • May 14, 2019
  • Remote Sensing
  • Mesay Belete Bejiga +2
  • Conference Article
  • Citations3

Exploiting Instance-based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-adaptive Action Detection

  • Jan 01, 2023
  • Yifan Lu +3
  • Dissertation

Towards robust sensing and recognition : from statistical learning to transfer learning

  • Jan 01, 2020
  • Jianfei Yang
  • Conference Article
  • Citations3

Reducing Annotation Effort by Identifying and Labeling Contextually Diverse Classes for Semantic Segmentation Under Domain Shift

  • Jan 01, 2023
  • Sharat Agarwal +2
  • Research Article
  • Citations35

A Bayesian-inspired, deep learning-based, semi-supervised domain adaptation technique for land cover mapping

  • Mar 04, 2021
  • Machine Learning
  • Benjamin Lucas +4
  • Research Article

Bi3D++: Hybrid Bi-Domain Active Learning for Cross-Domain 3D Object Detection.

  • Sep 01, 2026
  • IEEE transactions on pattern analysis and machine intelligence
  • Jiakang Yuan +6
  • Dissertation
  • Citations1

Domain adaptation and generalization for visual recognition

  • Jan 01, 2017
  • Li Niu
  • Research Article
  • Citations21

Source-free Style-diversity Adversarial Domain Adaptation with Privacy-preservation for person re-identification

  • Nov 04, 2023
  • Knowledge-Based Systems
  • Xiaofeng Qu +4
  • Research Article

PANDA: A Polarized Attention Network for Enhanced Unsupervised Domain Adaptation in Semantic Segmentation

  • Oct 31, 2024
  • Electronics
  • Chiao-Wen Kao +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.