EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

PMA-VQA: Progressive Multi-Scale Feature Fusion with Spatially Adaptive Attention for Remote Sensing Visual Question Answering

Yifei He iD, Chen Qiu iD, Jinguang Gu iD

Sensors · 10.04.2026 · 26 (8) · 2351

DOI: 10.3390/s26082351 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.04.2026. Verfasst von Yifei He und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, China. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Hubei Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing visual question answering (RS-VQA) is essential to intelligent Earth observation, as it supports interactive querying of high-resolution aerial images. Many existing methods struggle with fine-detail geospatial reasoning with remote sensing (RS) scenes due to RS scenes having intrinsic multi-scale object variance and pronounced spatial heterogeneity. The models tend to rely more on the linguistic prior than reasoning based on visual evidence. In this paper, we present PMA-VQA, a progressive multi-scale feature fusion with spatially adaptive attention, to embed the RS-VQA task in spatially based hierarchical feature integration. For hierarchical, multi-level, language-informed integration, we propose a spatial attention aggregation module (SAAM) and a progressive feature fusion and classification module (PFCM). The SAAM employs spatially adaptive gating to align cross-modal features with semantic context, while the PFCM integrates multi-scale representations across high-level semantic abstractions and low-level space. The experimental results on RS-VQA LR and HR benchmarks validate that PMA-VQA outperformed all competing methods in terms of accuracy and robustness. Evaluation of HRVQA further confirmed the effectiveness of the SAAM and PFCM across diverse RS scenes.

Schlagwörter

Stichwörter der Autor:innen

progressive multi-scale fusionremote sensing visual question answeringspatially adaptive attention

Autor:innen und Institutionen

  • School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, China.
  • Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System, Wuhan 430065, China.

ORCID-Profile: Yifei He, Chen Qiu, Jinguang Gu

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Hubei Province

Zitieren

APA

He, Y., Qiu, C., & Gu, J. (2026). PMA-VQA: Progressive Multi-Scale Feature Fusion with Spatially Adaptive Attention for Remote Sensing Visual Question Answering. Sensors, 26(8), 2351. https://doi.org/10.3390/s26082351

Vancouver

He Y, Qiu C, Gu J. PMA-VQA: Progressive Multi-Scale Feature Fusion with Spatially Adaptive Attention for Remote Sensing Visual Question Answering. Sensors. 2026;26(8):2351. doi:10.3390/s26082351

BibTeX
@article{He2026,
  author = {He, Yifei and Qiu, Chen and Gu, Jinguang},
  title = {PMA-VQA: Progressive Multi-Scale Feature Fusion with Spatially Adaptive Attention for Remote Sensing Visual Question Answering},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {8},
  pages = {2351},
  doi = {10.3390/s26082351}
}
Kostenlos starten →