Comparing Normalizing Flows and Deep Basis Pursuit
Angelos Georgios Koulouras, Jackson Lightfoot, Sami Khandker, Tarek Allam, Menelaos Kaskiris
The directories here are split as such:
- deepinpy_documentation: contains all newly generated documentation for the DeepInPy research project
- deepinpy_unet_implementation: contains all code related to the unet implementation added to deepinpy
- mcmri_preprocessing: Contains all code related to preprocessing the input data
- normalizing_flows_model: Contains all code related to the Normalizing Flows model
https://medium.com/@jaxon.lightfoot/improving-undersampled-mri-with-deep-learning-bf991672b006
[1] [1906.04032] Neural Spline Flows (Durkan et al.)
[2] [1905.11672] Invertible generative models for inverse problems: mitigating representation error and dataset bias (Asim et al.)
[3] [2003.08089] Compressed Sensing with Invertible Generative Models and Dependent Noise (Whang et al.)
[4] [1412.6980] Adam: A Method for Stochastic Optimization (Kingma and Ba)
[5] [1910.13110] Unsupervised Deep Basis Pursuit: Learning inverse problems without ground-truth data (Tamir et al.)
[6] [1505.04597] U-Net: Convolutional Networks for Biomedical Image Segmentation (Ronneberger et al.)
[7] Effectiveness of U-Net in Denoising RGB Images (Komatsu and Gonsalves)