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...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριος συγγραφέας:	HU Bin, WANG Xiaojun, ZHANG Lei
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	Editorial Office of Computer Engineering 2022-12-01
Σειρά:	Jisuanji gongcheng
Θέματα:	few-shot learning(fsl)|meta-learning|adversarial training|semi-supervised learning|adversarial robustness
Διαθέσιμο Online:	https://www.ecice06.com/fileup/1000-3428/PDF/20221214.pdf
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!