.png){kind=icon}
返回
Multi-semantic hypergraph neural network for effective few-shot learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109677.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recently, Graph-based Few-Shot Learning (FSL) methods exhibit good generalization by mining relations among few samples with Graph Neural Networks. However, most Graph-based FSL methods consider only binary relations and ignore the multi-semantic information of the global context knowledge. We propose a framework of Multi-Semantic Hypergraph for FSL (MSH-FSL) to explore complex latent high -order multi-semantic relations among the few samples. By mining the complex relationship structure of multi-node and multi-semantics, more refined feature representation can be learned, which yields better classification robustness. Specifically, we first construct a novel Multi-Semantic Hypergraph by obtain-ing associated instances with different semantic features via orthogonal mapping. With the constructed hypergraph, we then develop the Hyergraph Neural Network along with a novel multi-generation hyper -graph message passing so as to better leverage the complex latent semantic relations among samples. Finally, after a number of generations, the hyper-node representations embedded in the learned hyper -graph become more accurate for obtaining few-shot prediction. In the 5-way 1-shot task of ResNet-12 on mini-Imagenet dataset, the multi-semantic hypergraph outperforms single-semantic graph by 3.1%, and with the proposed semantic-distribution message passing, the improvement can further reach 6.1%.(c) 2023 Elsevier Ltd. All rights reserved.
Keyword:
Hypergraph
Few-shot learning
Multi-semantic learning
Orthogonal training
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
Piecewise Classifier Mappings: Learning Fine-Grained Learners for Novel Categories With Few Examples
OAAI
OAAI分享收藏SAPENet: Self-Attention based Prototype Enhancement Network for Few-shot LearningSAPENet: 基于自我注意的少镜头学习原型增强网络.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Few-shot prototype alignment regularization network for document image layout segementationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容