EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Game-Theoretic Multi-LLM Collaboration for Attribute-Aware Open-Vocabulary Object Detection

Risen Sheng, Jinming Pan, Zhuo Zeng, Hao Chen, Wenzhi Cao

Electronics · 26.06.2026 · 15 (13) · 2817

DOI: 10.3390/electronics15132817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 26.06.2026. Verfasst von Risen Sheng und 4 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key R&D Program, Xiangjiang Laboratory, Key Technologies and Applications of Holographic Media Creation Based on Multimodal Large AI Models.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Open-vocabulary object detection (OVD) fails at attribute-level discrimination: when instances share a class label yet differ in color, material, or texture, category names provide no appearance-specific cues. Prior attempts to enrich text inputs with LLM-generated descriptions are limited by single-model distribution bias, producing coverage gaps and unstable attribute quality. We propose a Concept Expander framework built on cooperative multi-LLM game theory. Three heterogeneous LLMs generate candidate attributes in parallel; a cooperative Nash equilibrium then selects the final subset by maximizing each model’s minimum utility gain, jointly enforcing semantic quality and cross-source diversity without amplifying any single model’s bias. The resulting Concept Repository contains approximately 5000 discriminative visual priors. A lightweight retrieval module injects the top-k matched attributes into region-level visual features via residual fusion, preserving CLIP’s pretrained alignment while enriching instance representations with fine-grained semantic priors. A semantic consistency loss anchors enhanced features to ground-truth class semantics throughout training. On LVIS, rare-category APr rises from 22.2 to 28.5; on RefCOCO, attribute-conditioned localization accuracy reaches 54.8, confirming that structured multi-LLM semantic priors improve discrimination across long-tail and high-confusion benchmarks.

Förderung

  • National Key R&D Program
  • Xiangjiang Laboratory
  • Key Technologies and Applications of Holographic Media Creation Based on Multimodal Large AI Models

Zitieren

APA

Sheng, R., Pan, J., Zeng, Z., Chen, H., & Cao, W. (2026). Game-Theoretic Multi-LLM Collaboration for Attribute-Aware Open-Vocabulary Object Detection. Electronics, 15(13), 2817. https://doi.org/10.3390/electronics15132817

Vancouver

Sheng R, Pan J, Zeng Z, Chen H, Cao W. Game-Theoretic Multi-LLM Collaboration for Attribute-Aware Open-Vocabulary Object Detection. Electronics. 2026;15(13):2817. doi:10.3390/electronics15132817

BibTeX
@article{Sheng2026,
  author = {Sheng, Risen and Pan, Jinming and Zeng, Zhuo and Chen, Hao and Cao, Wenzhi},
  title = {Game-Theoretic Multi-LLM Collaboration for Attribute-Aware Open-Vocabulary Object Detection},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {13},
  pages = {2817},
  doi = {10.3390/electronics15132817}
}
Kostenlos starten →