EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DARC: Lightweight Density-Adaptive Label Relation Calibration for Multi-Label Remote Sensing Scene Classification

Lan Ma, Yueyang Zhang, Ming Yu, Yujie Pi

Applied Sciences · 02.08.2026 · 16 (15) · 7681

DOI: 10.3390/app16157681 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 02.08.2026. Verfasst von Lan Ma und 3 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-label remote sensing scene classification requires identifying multiple land-cover categories from a single high-resolution aerial image. Existing methods strengthen visual features or model label dependencies, yet they apply a fixed calibration strategy regardless of the underlying label-density regime, leading to over-prediction on dense scenes or under-correction on sparse scenes. We propose Density-Adaptive CDG Calibration (DARC), a lightweight framework that explicitly conditions calibration on dataset label density. DARC comprises three modules: (1) Label-density Driven Profile Selection (DDP) automatically routes the calibration path based on training-set density statistics; (2) Label-token Correlative-Discriminative Graph Mixing (CDM) injects both co-occurrence and exclusivity relations into label semantic tokens through positive and negative graph propagation; (3) Density-aware Gated Calibration (DCM) applies cardinality-controlled gating for dense labels and EMA-stabilized graph calibration for sparse labels. Experiments on AID-ML and UCM-ML demonstrate that DARC achieves 90.12% and 89.05% sample-F1, respectively, outperforming six competitive baselines including SFIN, ASL, C-Tran, ML-Decoder, SPIN, and Two-Way Loss by 1.65–3.87%, while introducing only 1.42% additional parameters. Cross-regime routing analysis confirms that no single fixed strategy matches DARC’s adaptive approach, and sensitivity analysis shows the routing is robust across a wide threshold range. Ablation studies validate the necessity of each component, and visualization analyses demonstrate that the learned label graphs capture interpretable semantic patterns.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Ma, L., Zhang, Y., Yu, M., & Pi, Y. (2026). DARC: Lightweight Density-Adaptive Label Relation Calibration for Multi-Label Remote Sensing Scene Classification. Applied Sciences, 16(15), 7681. https://doi.org/10.3390/app16157681

Vancouver

Ma L, Zhang Y, Yu M, Pi Y. DARC: Lightweight Density-Adaptive Label Relation Calibration for Multi-Label Remote Sensing Scene Classification. Applied Sciences. 2026;16(15):7681. doi:10.3390/app16157681

BibTeX
@article{Ma2026,
  author = {Ma, Lan and Zhang, Yueyang and Yu, Ming and Pi, Yujie},
  title = {DARC: Lightweight Density-Adaptive Label Relation Calibration for Multi-Label Remote Sensing Scene Classification},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {7681},
  doi = {10.3390/app16157681}
}
Kostenlos starten →