Masked autoencoders are effective solution to transformer data-hungry

Vision Transformers (ViTs) outperforms convolutional neural networks (CNNs) in several vision tasks with its global modeling capabilities. However, ViT lacks the inductive bias inherent to convolution making it require a large amount of data for training. This results in ViT not performing as well a...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Mao, Jiawei, Zhou, Honggu, Yin, Xuesong, Xu, Yuanqi Chang. Binling Nie. Rui
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!