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...

Popoln opis

Shranjeno v:
Bibliografske podrobnosti
Glavni avtor: HU Bin, WANG Xiaojun, ZHANG Lei
Format: Artigo
Jezik:Inglês
Izdano: Editorial Office of Computer Engineering 2022-12-01
Serija:Jisuanji gongcheng
Teme:
few-shot learning(fsl)|meta-learning|adversarial training|semi-supervised learning|adversarial robustness
Online dostop:https://www.ecice06.com/fileup/1000-3428/PDF/20221214.pdf
Oznake: Označite
Brez oznak, prvi označite!

Podobne knjige/članki