arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.13474cs.LGcs.CV
收藏

基于概念的可解释原型网络的少样本学习

Interpretable Concept-based Prototypical Networks for Few-Shot Learning

Carleton University(卡尔顿大学)

Mohammad Reza Zarei, Majid Komeili

摘要:

少样本学习的目标是从有限样本的类中识别新的实例。这个具有挑战性的任务通常通过对类似任务执行元学习来减轻。然而,由此产生的模型是黑盒子。人们越来越担心部署黑盒机器学习模型,FSL在这方面也不例外。在本文中,我们提出了一种基于一组人类可解释的概念的FSL方法。它构造了一组与概念相关的度量空间,并通过聚合特定于概念的决策来对新类的样本进行分类。该方法不需要对查询样本进行概念标注。这种可解释的方法在CUB细粒度鸟类分类数据集上取得了与六种以前最先进的黑盒FSL方法相当的结果。

英文摘要:

Few-shot learning aims at recognizing new instances from classes with limited samples. This challenging task is usually alleviated by performing meta-learning on similar tasks. However, the resulting models are black-boxes. There has been growing concerns about deploying black-box machine learning models and FSL is not an exception in this regard. In this paper, we propose a method for FSL based on a set of human-interpretable concepts. It constructs a set of metric spaces associated with the concepts and classifies samples of novel classes by aggregating concept-specific decisions. The proposed method does not require concept annotations for query samples. This interpretable method achieved results on a par with six previously state-of-the-art black-box FSL methods on the CUB fine-grained bird classification dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑