BriefGPT.xyz
Jun, 2022
分布鲁棒模型的元分析
A Meta-Analysis of Distributionally-Robust Models
HTML
PDF
Benjamin Feuer, Ameya Joshi, Chinmay Hegde
TL;DR
通过 meta-analysis，我们发现具有良好 OOD 鲁棒性的最佳表现的模型都具有四个共同点，即视觉-语言预训练具有巨大的潜力。
Abstract
State-of-the-art
image classifiers
trained on massive datasets (such as ImageNet) have been shown to be vulnerable to a range of both intentional and incidental
distribution shifts
. On the other hand, several rec
→