Robustness of conditional GANs to noisy labels

Authors: Kiran K. Thekumparampil, Ashish Khetan, Zinan Lin, Sewoong Oh

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

Reproducibility Variable Result LLM Response
Research Type Experimental We show experimentally on MNIST and CIFAR-10 datasets that both the approaches consistently improve upon baseline approaches, and RCGAN-U closely matches the performance of RCGAN. 5 Experiments
Researcher Affiliation Academia University of Illinois at Urbana-Champaign, Carnegie Mellon University
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Code to reproduce our experiments is available at https://github.com/POLane16/Robust-Conditional-GAN.
Open Datasets Yes We show experimentally on MNIST and CIFAR-10 datasets that both the approaches consistently improve upon baseline approaches, and RCGAN-U closely matches the performance of RCGAN.
Dataset Splits No The paper mentions using training data and pre-trained classifiers for evaluation but does not specify explicit training/validation/test dataset splits for their own model training.
Hardware Specification Yes This work used the Extreme Science and Engineering Discovery Environment (XSEDE), which is supported by National Science Foundation grant number OCI-1053575. Specifically, it used the Bridges system, which is supported by NSF award number ACI-1445606, at the Pittsburgh Supercomputing Center (PSC).
Software Dependencies No The paper does not provide specific version numbers for software dependencies used in their implementation.
Experiment Setup No Implementation details are explained in Appendix L.