Can Un-trained Neural Networks Compete with Trained Neural Networks at Image Reconstruction?

07/06/2020 ∙ by Mohammad Zalbagi Darestani, et al. ∙ 42

Convolutional Neural Networks (CNNs) are highly effective for image reconstruction problems. Typically, CNNs are trained on large amounts of training images. Recently, however, un-trained neural networks such as the Deep Image Prior and Deep Decoder have achieved excellent image reconstruction performance for standard image reconstruction problems such as image denoising and image inpainting, without using any training data. This success raises the question whether un-trained neural networks can compete with trained ones for practical imaging tasks. To address this question, we consider accelerated magnetic resonance imaging (MRI), an important medical imaging problem, which has received significant attention from the deep-learning community, and for which a dedicated training set exists. We study and optimize un-trained architectures, and as a result, propose a variation of the architectures of the deep image prior and deep decoder. We show that the resulting convolutional decoder out-performs other un-trained methods and—most importantly—achieves on-par performance with a standard trained baseline, the U-net, on the FastMRI dataset, a new dataset for benchmarking deep learning based reconstruction methods. Besides achieving on-par reconstruction performance relative to trained methods, we demonstrate that a key advantage over trained methods is robustness to out-of-distribution examples.



There are no comments yet.


page 5

page 7

page 8

page 9

page 12

page 13

page 15

Code Repositories


Deep image prior for tomographic reconstruction

view repo


This project was done as a part of the course EE5180 taken in Jan-May 2021 at the Indian Institute of Technology, Madras

view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.