A study of the generalizability of self-supervised representations

Recent advancements in self-supervised learning (SSL) made it possible to learn generalizable visual representations from unlabeled data. The performance of Deep Learning models fine-tuned on pretrained SSL representations is on par with models fine-tuned on the state-of-the-art supervised learning...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Atharva Tendle, Mohammad Rashedul Hasan
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Elsevier 2021-12-01
Schriftenreihe:	Machine Learning with Applications
Schlagworte:	Self-supervised learning Supervised learning Transfer learning Generalizability Invariance
Online-Zugang:	http://www.sciencedirect.com/science/article/pii/S2666827021000621
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!