.png){kind=icon}
返回
Cycle optimization metric learning for few-shot classification *
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2023.109468.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Metric learning methods are widely used in few-shot learning due to their simplicity and effectiveness. Most existing methods directly predict query labels by comparing the similarity between support and query samples. In this paper, we design a cycle optimization metric network for few-shot classification task that optimizes model performance based on loop-prediction of the labels of query samples and support samples. Specifically, we construct a forward network and reverse network based on a geometric algebra Graph Neural Network (GA-GNN). These two networks form the loop prediction from support samples to query samples and then back to support samples, guided by a cycle-consistency loss. We also introduce an optimization module that is able to correct the predicted results of query samples to further improve the network performance. Our extensive experimental results demonstrate that the proposed cycle optimization metric network outperforms existing state-of-the-art few-shot learning methods on classification tasks.(c) 2023 Published by Elsevier Ltd.
Keyword:
Few-shot learning
Cycle optimization
Image classification
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Explainable deep learning for efficient and robust pattern recognition: A survey of recent developments可解释的深度学习用于高效和鲁棒的模式识别: 近期发展综述.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Self-augmentation: Generalizing deep networks to unseen classes for few-shot learningNEURAL NETWORKS
OAAI
NEURAL NETWORKSIF6.3
OAAI分享收藏
查看更多内容