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...

全面介紹

書目詳細資料

主要作者:	HU Bin, WANG Xiaojun, ZHANG Lei
格式:	Artigo
語言:	Inglês
出版:	Editorial Office of Computer Engineering 2022-12-01
叢編:	Jisuanji gongcheng
主題:	few-shot learning(fsl)|meta-learning|adversarial training|semi-supervised learning|adversarial robustness
在線閱讀:	https://www.ecice06.com/fileup/1000-3428/PDF/20221214.pdf
標簽:	添加標簽 沒有標簽, 成為第一個標記此記錄!