EUVIMEDEUVIMED entdecken
Crossref

Generating-Filtering-Ranking: A Three-Stage MultiModal Data Augmentation Framework Under Partial Modality Missing

Zhirui Kuai, Huan Zhang, Yang Yang, Yiping Ma, Mingjing Huang, Ning Gui, Li Kuang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5755-5763

DOI: 10.1609/aaai.v40i7.37496 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhirui Kuai und 6 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal data significantly improves the performance of pretrained models, but its practical application is often limited by missing or incomplete data across modalities. There are two key challenges that existing methods of synthesizing missing data face: (1) semantic inaccuracies due to model hallucinations and (2) discrepancies in distribution preferences between generated and original data. To address these challenges, we propose a novel three-stage multimodal data augmentation framework (GFR), which Generate, Filter, and Rank missing modality data. Our framework leverages multimodal large models for diverse data generation, designs a scene graph matching-based filtering algorithm to ensure semantic consistency, and constructs a preference-aware ranking model to align the generated data with both the original distribution and task relevance. Our framework not only enhances semantic diversity and consistency in data generation but also effectively captures the implicit characteristics of the original dataset and the target model. We demonstrate the effectiveness of GFR across multiple datasets by testing different missing types and missing ratios.

Zitieren

APA

Kuai, Z., Zhang, H., Yang, Y., Ma, Y., Huang, M., Gui, N., & Kuang, L. (2026). Generating-Filtering-Ranking: A Three-Stage MultiModal Data Augmentation Framework Under Partial Modality Missing. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5755-5763. https://doi.org/10.1609/aaai.v40i7.37496

Vancouver

Kuai Z, Zhang H, Yang Y, Ma Y, Huang M, Gui N, et al. Generating-Filtering-Ranking: A Three-Stage MultiModal Data Augmentation Framework Under Partial Modality Missing. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5755-5763. doi:10.1609/aaai.v40i7.37496

BibTeX
@article{Kuai2026,
  author = {Kuai, Zhirui and Zhang, Huan and Yang, Yang and Ma, Yiping and Huang, Mingjing and Gui, Ning and Kuang, Li},
  title = {Generating-Filtering-Ranking: A Three-Stage MultiModal Data Augmentation Framework Under Partial Modality Missing},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {7},
  pages = {5755--5763},
  doi = {10.1609/aaai.v40i7.37496}
}
Kostenlos starten →