EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SLA-YOLO—Enhancing YOLO for Tiny Defect Detection in Industrial Defect Scenes

Yanxia Lyu, Xinqi Wang, Chenyu Jin, Yuanhong Wei, Zhenyu Sun

Mathematics · 03.06.2026 · 14 (11) · 1973

DOI: 10.3390/math14111973 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Mathematics, online erschienen am 03.06.2026. Verfasst von Yanxia Lyu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 67 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation, Hebei Provincial Department of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In recent years, the YOLO series has emerged as a widely adopted framework for real-time object detection because of its favorable balance between detection accuracy and inference efficiency. Nevertheless, accurate recognition and localization of tiny defects in industrial inspection remain challenging. These challenges mainly arise from the extremely small scale of defect targets, low image contrast, and the limited capability of conventional models in feature representation under uniform backgrounds. To address these issues from a mathematically optimized perspective and via feature modeling optimization, we develop a dedicated framework for tiny defect detection, termed SLA-YOLO. The main contributions of this work are as follows. First, we adopt a slicing-based processing strategy inspired by the SAHI framework, referred to as Image Slicing Processing (ISP) in this work, and extend it to both training and inference stages. This design enhances the relative scale of tiny defects within local regions, improving detection sensitivity and data diversity without introducing additional model complexity. Second, we introduce a Large Receptive-Field Selective Context (LRSC) module. By leveraging large-receptive-field selective convolution kernels, this module adaptively captures contextual information around critical defect regions via feature modeling optimization of scale-dependent representations. Third, we incorporate a Transformer-based High-level Feature Enhancement (THFE) module to improve global dependency modeling in high-level semantic representations, thereby enhancing feature discriminability for complex defect patterns. Experimental results on the CCB defect dataset show that SLA-YOLO improves mAP@50:95 by 2.7% and mAP@50 by 3.3%. In addition, the proposed method demonstrates strong generalization capability on other tiny object detection tasks.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation
  • Hebei Provincial Department of Education

Zitieren

APA

Lyu, Y., Wang, X., Jin, C., Wei, Y., & Sun, Z. (2026). SLA-YOLO—Enhancing YOLO for Tiny Defect Detection in Industrial Defect Scenes. Mathematics, 14(11), 1973. https://doi.org/10.3390/math14111973

Vancouver

Lyu Y, Wang X, Jin C, Wei Y, Sun Z. SLA-YOLO—Enhancing YOLO for Tiny Defect Detection in Industrial Defect Scenes. Mathematics. 2026;14(11):1973. doi:10.3390/math14111973

BibTeX
@article{Lyu2026,
  author = {Lyu, Yanxia and Wang, Xinqi and Jin, Chenyu and Wei, Yuanhong and Sun, Zhenyu},
  title = {SLA-YOLO—Enhancing YOLO for Tiny Defect Detection in Industrial Defect Scenes},
  journal = {Mathematics},
  year = {2026},
  volume = {14},
  number = {11},
  pages = {1973},
  doi = {10.3390/math14111973}
}
Kostenlos starten →