BriefGPT.xyz
Oct, 2019
对抗性鲁棒少样本学习:一种元学习方法
Robust Few-Shot Learning with Adversarially Queried Meta-Learners
HTML
PDF
Micah Goldblum, Liam Fowl, Tom Goldstein
TL;DR
本研究旨在开发Adversarial Querying算法以生成对小样本图像分类具有鲁棒性的元学习器,并比较其与迁移学习方式的性能表现,结果表明在Mini-ImageNet和CIFAR-FS等图像分类任务上,该方法具有远优于传统迁移学习方法的鲁棒表现。
Abstract
Previous work on adversarially robust
neural networks
requires large training sets and computationally expensive training procedures. On the other hand,
few-shot learning
methods are highly vulnerable to adversar
→