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...

詳細記述

書誌詳細

第一著者:	HU Bin, WANG Xiaojun, ZHANG Lei
フォーマット:	Artigo
言語:	Inglês
出版事項:	Editorial Office of Computer Engineering 2022-12-01
シリーズ:	Jisuanji gongcheng
主題:	few-shot learning(fsl)|meta-learning|adversarial training|semi-supervised learning|adversarial robustness
オンライン･アクセス:	https://www.ecice06.com/fileup/1000-3428/PDF/20221214.pdf
タグ:	タグ追加 タグなし, このレコードへの初めてのタグを付けませんか!