Mutual-Information Based Few-Shot Classification

We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision loss based on the support set. We motivate our transductive l...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Boudiaf, Malik, Masud, Ziko Imtiaz, Rony, Jérôme, Dolz, Jose, Ayed, Ismail Ben, Piantanida, Pablo
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!