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...

Disgrifiad llawn

Wedi'i Gadw mewn:
Manylion Llyfryddiaeth
Prif Awdur: HU Bin, WANG Xiaojun, ZHANG Lei
Fformat: Artigo
Iaith:Inglês
Cyhoeddwyd: Editorial Office of Computer Engineering 2022-12-01
Cyfres:Jisuanji gongcheng
Pynciau:
few-shot learning(fsl)|meta-learning|adversarial training|semi-supervised learning|adversarial robustness
Mynediad Ar-lein:https://www.ecice06.com/fileup/1000-3428/PDF/20221214.pdf
Tagiau: Ychwanegu Tag
Dim Tagiau, Byddwch y cyntaf i dagio'r cofnod hwn!

Eitemau Tebyg