Adversarial Regularizers in Inverse Problems

Authors: Sebastian Lunz, Ozan Öktem, Carola-Bibiane Schönlieb

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments demonstrate the potential of the framework for denoising on the BSDS dataset and for computed tomography reconstruction on the LIDC dataset.
Researcher Affiliation Academia Sebastian Lunz DAMTP University of Cambridge Cambridge CB3 0WA lunz@math.cam.ac.uk Ozan Öktem Department of Mathematics KTH Royal Institute of Technology 100 44 Stockholm ozan@kth.se Carola-Bibiane Schönlieb DAMTP University of Cambridge Cambridge CB3 0WA cbs31@cam.ac.uk
Pseudocode Yes Algorithm 1 Learning a regularization functional
Open Source Code Yes The code is available online 1. https://github.com/lunz-s/Deep Adverserial Regulariser
Open Datasets Yes Experiments demonstrate the potential of the framework for denoising on the BSDS dataset and for computed tomography reconstruction on the LIDC dataset.
Dataset Splits No The paper uses the BSDS and LIDC datasets for experiments and mentions unsupervised training data but does not provide specific details on train/validation/test splits or a validation set.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No The paper mentions hyperparameters such as 'Gradient penalty coefficient µ, batch size m, Adam hyperparameters α' and 'regularization weight λ, step size ϵ' but does not provide their concrete values in the main text.