EUVIMEDEUVIMED entdecken
Crossref

RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images

Ke Li, Di Wang, Ting Wang, Fuyu Dong, Yiming Zhang, Luyao Zhang, Xiangyu Wang, Shaofeng Li, Quan Wang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (8) · 6288-6296

DOI: 10.1609/aaai.v40i8.37555 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Ke Li und 8 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing visual grounding (RSVG) aims to localize objects in remote sensing images based on free-form natural language expressions. Existing approaches are typically constrained to closed-set vocabularies, limiting their applicability in open-world scenarios. While recent attempts to leverage generic foundation models for open-vocabulary RSVG, they overly rely on expensive high-quality datasets and time-consuming fine-tuning. To address these limitations, we propose RSVG-ZeroOV, a training-free framework that aims to explore the potential of frozen generic foundation models for zero-shot open-vocabulary RSVG. Specifically, RSVG-ZeroOV comprises three key stages: (i) Overview: We utilize a vision-language model (VLM) to obtain cross-attention maps that capture semantic correlations between text queries and visual regions. (ii) Focus: By leveraging the fine-grained modeling priors of a diffusion model (DM), we fill in gaps in structural and shape information of objects, which are often overlooked by VLM. (iii) Evolve: A simple yet effective attention evolution module is introduced to suppress irrelevant activations, yielding purified segmentation masks over the referred objects. Without cumbersome task-specific training, RSVG-ZeroOV offers an efficient and scalable solution. Extensive experiments demonstrate that the proposed framework consistently outperforms existing weakly-supervised and zero-shot methods.

Zitieren

APA

Li, K., Wang, D., Wang, T., Dong, F., Zhang, Y., Zhang, L., Wang, X., Li, S., & Wang, Q. (2026). RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images. Proceedings of the AAAI Conference on Artificial Intelligence, 40(8), 6288-6296. https://doi.org/10.1609/aaai.v40i8.37555

Vancouver

Li K, Wang D, Wang T, Dong F, Zhang Y, Zhang L, et al. RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(8):6288-6296. doi:10.1609/aaai.v40i8.37555

BibTeX
@article{Li2026,
  author = {Li, Ke and Wang, Di and Wang, Ting and Dong, Fuyu and Zhang, Yiming and Zhang, Luyao and Wang, Xiangyu and Li, Shaofeng and Wang, Quan},
  title = {RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {8},
  pages = {6288--6296},
  doi = {10.1609/aaai.v40i8.37555}
}
Kostenlos starten →