Robust Meta-learning with Sampling Noise and Label Noise via Eigen-ReptileDownload PDFOpen Website

2022 (modified: 19 Apr 2023)ICML 2022Readers: Everyone
Abstract: Recent years have seen a surge of interest in meta-learning techniques for tackling the few-shot learning (FSL) problem. However, the meta-learner is prone to overfitting since there are only a few...
0 Replies

Loading