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...

Celý popis

Uloženo v:
Podrobná bibliografie
Hlavní autor: HU Bin, WANG Xiaojun, ZHANG Lei
Médium: Artigo
Jazyk:Inglês
Vydáno: Editorial Office of Computer Engineering 2022-12-01
Edice:Jisuanji gongcheng
Témata:
few-shot learning(fsl)|meta-learning|adversarial training|semi-supervised learning|adversarial robustness
On-line přístup:https://www.ecice06.com/fileup/1000-3428/PDF/20221214.pdf
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo otaguje tento záznam!

Podobné jednotky