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 labeled training...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолч:	HU Bin, WANG Xiaojun, ZHANG Lei
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	Editorial Office of Computer Engineering 2022-12-01
Цуврал:	Jisuanji gongcheng
Нөхцлүүд:	few-shot learning(fsl)|meta-learning|adversarial training|semi-supervised learning|adversarial robustness
Онлайн хандалт:	https://www.ecice06.com/fileup/1000-3428/PDF/20221214.pdf
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!