EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Co-Training Vision-Language Models for Remote Sensing Multi-Task Learning

Qingyun Li, Shuran Ma, Junwei Luo, Yi Yu, Yue Zhou, Fengxiang Wang, Xudong Lu, Xiaoxing Wang, Xin He, Yushi Chen, Xue Yang

Remote Sensing · 09.01.2026 · 18 (2) · 222

DOI: 10.3390/rs18020222 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 09.01.2026. Verfasst von Qingyun Li und 10 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 85 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shanghai.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

With Transformers achieving outstanding performance on individual remote sensing (RS) tasks, we are now approaching the realization of a unified model that excels across multiple tasks through multi-task learning (MTL). Compared to single-task approaches, MTL methods offer improved generalization, enhanced scalability, and greater practical applicability. Recently, vision-language models (VLMs) have achieved promising results in RS image understanding, grounding, and ultra-high-resolution (UHR) image reasoning, respectively. Moreover, the unified text-based interface demonstrates significant potential for MTL. Hence, in this work, we present RSCoVLM, a simple yet flexible VLM baseline for RS MTL. Firstly, we create the data curation procedure, including data acquisition, offline processing and integrating, as well as online loading and weighting. This data procedure effectively addresses complex RS data enviroments and generates flexible vision-language conversations. Furthermore, we propose a unified dynamic-resolution strategy to address the diverse image scales inherent in RS imagery. For UHR images, we introduce the Zoom-in Chain mechanism together with its corresponding dataset, LRS-VQA-Zoom. The strategies are flexible and effectively mitigate the computational burdens. Additionally, we significantly enhance the model’s object detection capability and propose a novel evaluation protocol that ensures fair comparison between VLMs and conventional detection models. Extensive experiments demonstrate that RSCoVLM achieves state-of-the-art performance across diverse tasks, outperforming existing RS VLMs and even rivaling specialized expert models. All the training and evaluating tools, model weights, and datasets have been fully open-sourced to support reproducibility. We expect that this baseline will promote further progress toward general-purpose RS models.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Shanghai

Zitieren

APA

Li, Q., Ma, S., Luo, J., Yu, Y., Zhou, Y., Wang, F., Lu, X., Wang, X., He, X., Chen, Y., & Yang, X. (2026). Co-Training Vision-Language Models for Remote Sensing Multi-Task Learning. Remote Sensing, 18(2), 222. https://doi.org/10.3390/rs18020222

Vancouver

Li Q, Ma S, Luo J, Yu Y, Zhou Y, Wang F, et al. Co-Training Vision-Language Models for Remote Sensing Multi-Task Learning. Remote Sensing. 2026;18(2):222. doi:10.3390/rs18020222

BibTeX
@article{Li2026,
  author = {Li, Qingyun and Ma, Shuran and Luo, Junwei and Yu, Yi and Zhou, Yue and Wang, Fengxiang and Lu, Xudong and Wang, Xiaoxing and He, Xin and Chen, Yushi and Yang, Xue},
  title = {Co-Training Vision-Language Models for Remote Sensing Multi-Task Learning},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {2},
  pages = {222},
  doi = {10.3390/rs18020222}
}
Kostenlos starten →