SpectFormer: Frequency and Attention is what you need in a Vision Transformer

Vision transformers have been applied successfully for image recognition tasks. There have been either multi-headed self-attention based (ViT \cite{dosovitskiy2020image}, DeIT, \cite{touvron2021training}) similar to the original work in textual models or more recently based on spectral layers (Fnet\...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Patro, Badri N, Namboodiri, Vinay P, Agneeswaran, Vijay Srinivas
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!