EUVIMEDEUVIMED entdecken
Crossref

MPA: Multimodal Prototype Augmentation for Few-Shot Learning

Liwen Wu, Wei Wang, Lei Zhao, Zhan Gao, Qika Lin, Shaowen Yao, Zuozhu Liu, Bin Pu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (32) · 26965-26973

DOI: 10.1609/aaai.v40i32.39909 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Liwen Wu und 7 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, Few-shot Learning (FSL) has become a popular task that aims to recognize new classes from only a few labeled examples and has been widely applied in fields such as natural science, remote sensing, and medical images. However, most existing methods focus only on the visual modality and compute prototypes directly from raw support images, which lack comprehensive and rich multimodal information. To address these limitations, we propose a novel Multimodal Prototype Augmentation FSL framework called MPA, including LLM-based Multi-Variant Semantic Enhancement (LMSE), Hierarchical Multi-View Augmentation (HMA), and an Adaptive Uncertain Class Absorber (AUCA). LMSE leverages large language models to generate diverse paraphrased category descriptions, enriching the support set with additional semantic cues. HMA exploits both natural and multi-view augmentations to enhance feature diversity (e.g., changes in viewing distance, camera angles, and lighting conditions). AUCA models uncertainty by introducing uncertain classes via interpolation and Gaussian sampling, effectively absorbing uncertain samples. Extensive experiments on four single-domain and six cross-domain FSL benchmarks demonstrate that MPA achieves superior performance compared to existing state-of-the-art methods across most settings. Notably, MPA surpasses the second-best method by 12.29% and 24.56% in the single-domain and cross-domain setting, respectively, in the 5-way 1-shot setting.

Zitieren

APA

Wu, L., Wang, W., Zhao, L., Gao, Z., Lin, Q., Yao, S., Liu, Z., & Pu, B. (2026). MPA: Multimodal Prototype Augmentation for Few-Shot Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(32), 26965-26973. https://doi.org/10.1609/aaai.v40i32.39909

Vancouver

Wu L, Wang W, Zhao L, Gao Z, Lin Q, Yao S, et al. MPA: Multimodal Prototype Augmentation for Few-Shot Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(32):26965-26973. doi:10.1609/aaai.v40i32.39909

BibTeX
@article{Wu2026,
  author = {Wu, Liwen and Wang, Wei and Zhao, Lei and Gao, Zhan and Lin, Qika and Yao, Shaowen and Liu, Zuozhu and Pu, Bin},
  title = {MPA: Multimodal Prototype Augmentation for Few-Shot Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {32},
  pages = {26965--26973},
  doi = {10.1609/aaai.v40i32.39909}
}
Kostenlos starten →