Compositional Prototypical Networks for Few-Shot Classification
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (7) · 9011-9019
DOI: 10.1609/aaai.v37i7.26082 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Qiang Lyu und 1 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref).
Abstract (Originalsprache)
It is assumed that pre-training provides the feature extractor with strong class transferability and that high novel class generalization can be achieved by simply reusing the transferable feature extractor. In this work, our motivation is to explicitly learn some fine-grained and transferable meta-knowledge so that feature reusability can be further improved. Concretely, inspired by the fact that humans can use learned concepts or components to help them recognize novel classes, we propose Compositional Prototypical Networks (CPN) to learn a transferable prototype for each human-annotated attribute, which we call a component prototype. We empirically demonstrate that the learned component prototypes have good class transferability and can be reused to construct compositional prototypes for novel classes. Then a learnable weight generator is utilized to adaptively fuse the compositional and visual prototypes. Extensive experiments demonstrate that our method can achieve state-of-the-art results on different datasets and settings. The performance gains are especially remarkable in the 5-way 1-shot setting. The code is available at https://github.com/fikry102/CPN.
Zitieren
APA
Lyu, Q., & Wang, W. (2023). Compositional Prototypical Networks for Few-Shot Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 37(7), 9011-9019. https://doi.org/10.1609/aaai.v37i7.26082
Vancouver
Lyu Q, Wang W. Compositional Prototypical Networks for Few-Shot Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(7):9011-9019. doi:10.1609/aaai.v37i7.26082
BibTeX
@article{Lyu2023,
author = {Lyu, Qiang and Wang, Weiqiang},
title = {Compositional Prototypical Networks for Few-Shot Classification},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {7},
pages = {9011--9019},
doi = {10.1609/aaai.v37i7.26082}
}
EUVIMED