Self-Masking Networks for Unsupervised Adaptation

With the advent of billion-parameter foundation models, efficient fine-tuning has become increasingly important for the adaptation of models to downstream tasks. However, especially in computer vision, it can be hard to achieve good performance when access to quality labeled data is lacking. In this...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-09
Hauptverfasser:	Alfonso Taboada Warmerdam, Caron, Mathilde, Asano, Yuki M
Format:	Artikel
Sprache:	eng
Schlagworte:	Adaptation Computer vision Labels Learning Masking Masks Performance enhancement
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!