Distribution Estimation Based Pseudo-Feature Library Generation For Few-Shot Image Classification

2021 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)(2021)

引用 3|浏览11
暂无评分
摘要
Due to the high cost of labeled data acquisition, few-shot learning has attracted great attention in recent years. The biased estimation of class distribution from a few labeled samples hinders the model’s performance. Some existing methods generate samples or features by a learning module or network. In this paper, a distribution-based pseudo-feature library generation method is proposed, and it ...
更多
查看译文
关键词
Training,Conferences,Data acquisition,Estimation,Libraries,Task analysis,Image classification
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要