User: Guest  Login
Title:

Vision Transformers Enable Fast and Robust Accelerated MRI

Document type:
Konferenzbeitrag
Author(s):
Lin, Kang; Heckel, Reinhard
Abstract:
The Vision Transformer, when trained or pre-trained on datasets consisting of millions of images, gives excellent accuracy for image classification tasks and offers computational savings relative to convolutional neural networks. Motivated by potential accuracy gains and computational savings, we study Vision Transformers for accelerated magnetic resonance image reconstruction. We show that, when trained on the fastMRI dataset, a popular dataset for accelerated MRI only consisting of thousands o...     »
Keywords:
Accelerated MRI, Transformer, pre-training, image reconstruction
Book / Congress title:
MIDL 2022 Conference Submission
Year:
2021
WWW:
https://openreview.net/forum?id=cNX6LASbv6
 BibTeX