当前位置: X-MOL 学术Displays › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A metric-based meta-learning approach combined attention mechanism and ensemble learning for few-shot learning
Displays ( IF 3.7 ) Pub Date : 2021-09-20 , DOI: 10.1016/j.displa.2021.102065
Nan Guo 1, 2, 3, 4, 5 , Kexin Di 1 , Hongyan Liu 1, 2, 3, 4, 5 , Yifei Wang 1 , Junfei Qiao 1, 2, 3, 4, 5
Affiliation  

Meta-learning is one of the latest research directions in machine learning, which is considered to be one of the most probably ways to realize strong artificial intelligence. Meta-learning focuses on seeking solutions for machines to learn like human beings do - to recognize things through only few sample data and quickly adapt to new tasks. Challenges occur in how to train an efficient machine model with limited labeled data, since the model is easily over-fitted. In this paper, we address this obvious but important problem and propose a metric-based meta-learning model, which combines attention mechanisms and ensemble learning method. In our model, we first design a dual path attention module which considers both channel attention and spatial attention module, and the attention modules have been stacked to conduct a meta-learner for few shot meta-learning. Then, we apply an ensemble method called snap-shot ensemble to the attention-based meta-learner in order to generate more models in a single episode. Features abstracted from the models are put into the metric-based architecture to compute a prototype for each class. Our proposed method intensifies the feature extracting ability of backbone network in meta-learner and reduces over-fitting through ensemble learning and metric learning method. Experimental results toward several meta-learning datasets show that our approach is effective.



中文翻译:

基于度量的元学习方法将注意力机制和集成学习相结合,用于小样本学习

元学习是机器学习的最新研究方向之一,被认为是最有可能实现强人工智能的方法之一。元学习专注于为机器寻找解决方案,使其像人类一样学习——仅通过少量样本数据来识别事物并快速适应新任务。在如何使用有限的标记数据训练高效的机器模型方面存在挑战,因为该模型很容易过拟合。在本文中,我们解决了这个明显但重要的问题,并提出了一种基于度量的元学习模型,该模型结合了注意力机制和集成学习方法。在我们的模型中,我们首先设计了一个双路径注意力模块,它同时考虑了通道注意力和空间注意力模块,并且注意力模块已经被堆叠起来以进行元学习器进行少量元学习。然后,我们将一种称为 snap-shot ensemble 的集成方法应用于基于注意力的元学习器,以便在单个情节中生成更多模型。从模型中抽象出来的特征被放入基于度量的架构中,以计算每个类的原型。我们提出的方法增强了元学习器中骨干网络的特征提取能力,并通过集成学习和度量学习方法减少了过度拟合。对几个元学习数据集的实验结果表明我们的方法是有效的。从模型中抽象出来的特征被放入基于度量的架构中,以计算每个类的原型。我们提出的方法增强了元学习器中骨干网络的特征提取能力,并通过集成学习和度量学习方法减少了过度拟合。对几个元学习数据集的实验结果表明我们的方法是有效的。从模型中抽象出来的特征被放入基于度量的架构中,以计算每个类的原型。我们提出的方法增强了元学习器中骨干网络的特征提取能力,并通过集成学习和度量学习方法减少了过度拟合。对几个元学习数据集的实验结果表明我们的方法是有效的。

更新日期:2021-10-09
down
wechat
bug