A Semi-Supervised Adversarial Robust Model-Agnostic Meta-Learning Method

The meta model developed by meta learning is expected to have the ability of "learning to learn". Therefore, it can quickly adapt to new tasks based on the learned "meta knowledge", with a small number of gradient descent steps to fine-tune the model using a few l...

Full description

Saved in:
Bibliographic Details
Main Author: HU Bin, WANG Xiaojun, ZHANG Lei
Format: Artigo
Language:Inglês
Published: Editorial Office of Computer Engineering 2022-12-01
Series:Jisuanji gongcheng
Subjects:
few-shot learning(fsl)|meta-learning|adversarial training|semi-supervised learning|adversarial robustness
Online Access:https://www.ecice06.com/fileup/1000-3428/PDF/20221214.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!

Similar Items