Dynamic Knowledge Path Learning for Few-Shot Learning
简介：Few-shot learning is a challenging task that aims to train a classifier with very limited training samples.Most existing few-shot learning methods mainly focus on mining knowledge from limited training samples as much as possible and ignore the learning order.Inspired by human learning,people select useful knowledge and follow a learning path to enhance their learning ability.In this paper.we propose a novel few-shot learning model called dynamic knowledge path learning(DKPL)to guide the few-shot learning task to learn useful selected knowledge with suitable learning paths.Specifically,we simultaneously consider the importance,direction,and diversity of knowledge and propose a dynamic path learning strategy in the dynamic path construction module.Furthermore,we design a new learner to absorb knowledge,step by step,according to each class's learning path in the knowledge path propagation module.As far as we know,this is the first few-shot learning work to consider dynamic path learning to improve classification accuracy.Experiments and visual case studies demonstrate the effectiveness and superiority of the DKPL model on four real-world image datasets.展开
学者：JingzhuLIZheYinXUYangJianbinJiaoYEDing
关键词：data miningfew-shot learningimage classification
在线出版日期：2025-06-13 （网站首发日期）
