Compositional Prototypical Networks for Few-Shot Classification

Qiang Lyu,Weiqiang Wang

CoRR(2023)

引用 2|浏览38
暂无评分
摘要
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.
更多
查看译文
关键词
classification,networks,few-shot
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要