Reducing the covariate shift by mirror samples in cross domain alignment

Y Zhao, L Cai - Advances in Neural Information …, 2021 - proceedings.neurips.cc
Eliminating the covariate shift cross domains is one of the common methods to deal with the
issue of domain shift in visual unsupervised domain adaptation. However, current alignment …

Weighted meta-learning

D Cai, R Sheth, L Mackey, N Fusi - arXiv preprint arXiv:2003.09465, 2020 - arxiv.org
Meta-learning leverages related source tasks to learn an initialization that can be quickly
fine-tuned to a target task with limited labeled examples. However, many popular meta …