Task Attribute Distance for Few-Shot Learning: Theoretical Analysis and Applications

arXiv:2403.03535v1 Announce Type: cross
Abstract: Few-shot learning (FSL) aims to learn novel tasks with very few labeled samples by leveraging experience from \emph{related} training tasks. In this paper, we try to understand FSL by delving into two key questions: (1) How to quantify the relationship between \emph{training} and \emph{novel} tasks? (2) How does the relationship affect the \emph{adaptation difficulty} on novel tasks for different models? To answer the two questions, we introduce Task Attribute Distance (TAD) built upon attributes as …

analysis applications arxiv cs.cv cs.lg few-shot few-shot learning type