.png){kind=icon}
返回
Mutual Correlation Network for few-shot learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106289.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Most metric -based Few -Shot Learning (FSL) methods focus on learning good embeddings of images. However, these methods either lack the ability to explore the cross -correlation (i.e., correlated information) between image pairs or explore limited consensus among the correlation map constrained by the limited receptive field of CNN. We propose a Mutual Correlation Network (MCNet) to explore global consensus among the correlation map by using the self -attention mechanism which has a global receptive field. Our MCNet contains two core modules: (1) a multi -level embedding module that generates multi -level embeddings for an image pair which capture hierarchical semantics, and (2) a mutual correlation module that refines correlation map of two embeddings and generates more robust relational embeddings. Extensive experiments show that our MCNet achieves competitive results on four widely -used few -shot classification benchmarks miniImageNet, tieredImageNet, CUB -200-2011, and CIFAR-FS. Code is available at https://github.com/DRGreat/MCNet.
Keyword:
Few-shot classification
Mutual correlation
Multi-level embedding
Self-attention mechanism
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
机构
暂无机构信息
引用论文
Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
PREAI
分享收藏Few-shot remote sensing image scene classification based on multiscale covariance metric network (MCMNet).png)
NEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏
Synthesis of a new fluorelastomer from tetrafluoroethylene and propylene by radiation processing
PREAI
分享收藏
查看更多内容