Task-Aware Compressed Sensing With Generative Adversarial Networks

Authors: Maya Kabkab, Pouya Samangouei, Rama Chellappa

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

Reproducibility Variable Result LLM Response
Research Type Experimental We demonstrate the effectiveness of our method on a variety of reconstruction and classification problems.
Researcher Affiliation Academia Maya Kabkab, Pouya Samangouei, Rama Chellappa Department of Electrical and Computer Engineering University of Maryland Institute for Advanced Computer Studies University of Maryland, College Park, MD 20742 {mayak, pouya, rama}@umiacs.umd.edu
Pseudocode Yes Algorithm 1 Task-aware GAN training algorithm.
Open Source Code Yes Our code has been made publicly available at https://github.com/po0ya/csgan.
Open Datasets Yes In our experiments, we use three different image datasets: the MNIST handwritten digits dataset [Le Cun et al., 1998], the Fashion-MNIST (F-MNIST) clothing articles dataset [Xiao, Rasul, and Vollgraf, 2017], and the Celeb Faces Attributes dataset (Celeb A) [Liu et al., 2015].
Dataset Splits Yes The MNIST and F-MNIST datasets each consists of 60, 000 training images and 10, 000 testing images, each of size 28 28. We split the training images into a training set of 50, 000 images and hold-out a validation set containing 10, 000 images. The testing set is kept the same.
Hardware Specification No The paper mentions implementation details and hyperparameters are in the code repository, but does not specify the hardware used for experiments.
Software Dependencies No The paper mentions 'Tensor Flow' but does not specify a version number or other software dependencies with versions.
Experiment Setup No The paper states that 'Details of the hyper-parameters used in our experiments can be found in the code repository' but does not list them directly in the main text.