EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

UniRS-Seg: Shared Sparse–Dense Query Decoding for Joint Semantic and Referring Remote Sensing Segmentation

Aya Taourirte, Hai Huan

Remote Sensing · 24.10.2026 · 18 (21) · 3658

DOI: 10.3390/rs18213658 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.10.2026. Verfasst von Aya Taourirte und 1 weiteren Autor:innen. Die Arbeit nennt 60 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing semantic and referring segmentation share mask geometry but differ in whether a category vocabulary or a natural-language expression selects the output. UniRS-Seg bridges these interfaces through a shared sparse–dense query compiler and a hierarchical mask decoder, jointly trained on independently annotated datasets. Class names and referring expressions are projected from SigLIP 2 into the same decoder space; dense image–query activations supply spatial support, and sparse query tokens specify the requested region. An adapted SAM ViT-B pathway and parallel convolutional features recover local geometry, while learnable soft mask cross-attention refines both tasks and class-balanced mask-guided self-attention supports semantic parsing. UniRS-Seg achieves 57.30%, 85.31%, and 88.24% mIoU on LoveDA, Vaihingen, and Potsdam, and 78.18% and 70.88% gIoU on RefSegRS and RRSIS-D. These scores exceed the strongest listed baseline means by 0.68, 0.99, 1.18, 0.79, and 1.71 percentage points, respectively. Against separately trained semantic-only and referring-only versions of the shared architecture, joint training improves the four evaluated datasets by 0.45, 0.89, 1.40, and 0.97 points. An additional supervised RISBench evaluation achieves 72.91% gIoU and 74.85% cIoU, with the highest gIoU among the listed methods. On RefSegRS, adding learnable mask cross-attention to combined sparse and dense prompts increases gIoU by 0.86 points. The results support supervised dual-task transfer through a common query-conditioned decoder; the comparison uses published baseline results and does not establish unseen-domain or zero-shot generalization.

Zitieren

APA

Taourirte, A., & Huan, H. (2026). UniRS-Seg: Shared Sparse–Dense Query Decoding for Joint Semantic and Referring Remote Sensing Segmentation. Remote Sensing, 18(21), 3658. https://doi.org/10.3390/rs18213658

Vancouver

Taourirte A, Huan H. UniRS-Seg: Shared Sparse–Dense Query Decoding for Joint Semantic and Referring Remote Sensing Segmentation. Remote Sensing. 2026;18(21):3658. doi:10.3390/rs18213658

BibTeX
@article{Taourirte2026,
  author = {Taourirte, Aya and Huan, Hai},
  title = {UniRS-Seg: Shared Sparse–Dense Query Decoding for Joint Semantic and Referring Remote Sensing Segmentation},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {21},
  pages = {3658},
  doi = {10.3390/rs18213658}
}
Kostenlos starten →