EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Enhancing End-to-End Graphite Ore Grade Detection via Boundary-Aware Refinement, Bidirectional Fusion, and Difficulty-Aware Distillation

Yanwu Yi, Binghui Wei, Zeyang Qiu, Chen Yang, Xueyu Huang

Applied Sciences · 21.08.2026 · 16 (16) · 8332

DOI: 10.3390/app16168332 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 21.08.2026. Verfasst von Yanwu Yi und 4 weiteren Autor:innen. Die Arbeit nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Science and Technology Project of Yichun City.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graphite ore grade sorting is a key step toward intelligent mineral processing; however, it faces three representational contradictions: ambiguous classification posteriors at grade boundaries, asymmetric multi-scale feature interaction, and the mismatch between class-agnostic self-distillation assignment and sample-level difficulty. Targeting these, this paper adopts D-FINE as the baseline and introduces three decoupled improvements at its decoder, encoder, and criterion layers. (1) Boundary-Grade-aware Distribution Refinement (BG-FDR) online identifies boundary samples via the Top-2 classification score gap and modulates regression-distribution refinement, yielding +2.69 percentage points in mAP@0.5 with zero additional trainable parameters. (2) Bidirectional Feature Pyramid with Global–Local Spatial Attention (BiFPN-GLSA) builds a learnable weighted bidirectional multi-scale fusion path. (3) Difficulty-Aware Decoupled Distillation with Wise-Inner-Shape-IoU (DADD+Wise-IoU) imposes class- and sample-level difficulty-aware constraints. In the integrated full model, this increases Precision from 66.21% to 71.43% (+5.22 pp), F1 from 73.57% to 77.57%, and mean IoU from 97.81% to 98.35%, while false positives drop by 19.6%; the only parameter overhead (+3.84M) comes from BiFPN-GLSA, with BG-FDR and DADD adding effectively no network weights. Ablation on a self-built 3800-image dataset reveals a non-monotonic AP–Precision relationship: the mAP-optimal configuration (BG-FDR+BiFPN-GLSA, 94.17%) and the Precision-optimal one (DADD+Wise-IoU, 77.54%) do not coincide, providing a quantitative basis for objective-driven module selection in industrial sorting.

Förderung

  • Key Science and Technology Project of Yichun City

Zitieren

APA

Yi, Y., Wei, B., Qiu, Z., Yang, C., & Huang, X. (2026). Enhancing End-to-End Graphite Ore Grade Detection via Boundary-Aware Refinement, Bidirectional Fusion, and Difficulty-Aware Distillation. Applied Sciences, 16(16), 8332. https://doi.org/10.3390/app16168332

Vancouver

Yi Y, Wei B, Qiu Z, Yang C, Huang X. Enhancing End-to-End Graphite Ore Grade Detection via Boundary-Aware Refinement, Bidirectional Fusion, and Difficulty-Aware Distillation. Applied Sciences. 2026;16(16):8332. doi:10.3390/app16168332

BibTeX
@article{Yi2026,
  author = {Yi, Yanwu and Wei, Binghui and Qiu, Zeyang and Yang, Chen and Huang, Xueyu},
  title = {Enhancing End-to-End Graphite Ore Grade Detection via Boundary-Aware Refinement, Bidirectional Fusion, and Difficulty-Aware Distillation},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {16},
  pages = {8332},
  doi = {10.3390/app16168332}
}
Kostenlos starten →