EUVIMEDEUVIMED entdecken
Crossref

Cross-Facility Reliable Deep Learning-Based Beef Marbling Assessment Via Unsupervised Domain Adaptation Regression

Samuel Vinson, Dongyi Wang

Journal of the ASABE · 2026 · 69 (2) · 233-239

DOI: 10.13031/ja.16569 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the ASABE, 2026. Verfasst von Samuel Vinson und 1 weiteren Autor:innen. Gefördert von: USDA.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Highlights First unsupervised domain adaptation applied to beef marbling prediction. ResNet-50 DA model reduces cross-facility grading variability significantly. Improved accuracy across plants despite lighting and operational differences. Framework supports scalable, fair USDA beef grading and supply chain adoption. ABSTRACT. Inconsistent quality grading in beef production leads to inefficiencies, economic disparity, and consumer mistrust. While USDA meat grading traditionally relies on skilled visual inspectors, these human evaluations suffer from cross-facility variability and subjectivity. This paper introduces the first known application of unsupervised domain adaptation regression for cross-facility beef marbling score prediction. This is an innovation that improves generalization across diverse environments in the beef supply chain. Utilizing numerical scores ranging from 100 to 900, the research employed convolutional neural networks (CNNs), including ResNet, VGG, and AlexNet architectures. The study specifically introduced and validated a unified unsupervised domain adaptation regression method using the ResNet-50 architecture to enhance model generalization across diverse environments, accounting for variations in lighting, equipment, and operational practices. Statistical analyses demonstrated that the deep learning approach significantly reduces prediction error relative to human-assigned marbling scores, improving consistency across facilities. The proposed domain adaptation model notably outperformed conventional CNN approaches, offering a scalable, robust, and practical solution for widespread industry adoption. Beyond automating grading, this work lays a foundation for scalable machine vision systems in livestock and distribution logistics, with implications for robotics, food equity, and next-generation supply chain automation. Keywords: Adversarial learning, Beef carcass grading, Computer vision, Cross-facility generalization, Deep learning, Domain adaptation, Marbling score prediction, Unsupervised learning, USDA grading.

Förderung

  • USDA

Zitieren

APA

Vinson, S., & Wang, D. (2026). Cross-Facility Reliable Deep Learning-Based Beef Marbling Assessment Via Unsupervised Domain Adaptation Regression. Journal of the ASABE, 69(2), 233-239. https://doi.org/10.13031/ja.16569

Vancouver

Vinson S, Wang D. Cross-Facility Reliable Deep Learning-Based Beef Marbling Assessment Via Unsupervised Domain Adaptation Regression. Journal of the ASABE. 2026;69(2):233-239. doi:10.13031/ja.16569

BibTeX
@article{Vinson2026,
  author = {Vinson, Samuel and Wang, Dongyi},
  title = {Cross-Facility Reliable Deep Learning-Based Beef Marbling Assessment Via Unsupervised Domain Adaptation Regression},
  journal = {Journal of the ASABE},
  year = {2026},
  volume = {69},
  number = {2},
  pages = {233--239},
  doi = {10.13031/ja.16569}
}
Kostenlos starten →