Papers › PacGAN: The power of two samples in generative adversarial networks

PacGAN: The power of two samples in generative adversarial networks

12 Dec 2017NeurIPS 2018 12arXiv:1712.04086archive 2025-07-28

Zinan Lin, Ashish Khetan, Giulia Fanti, Sewoong Oh

Generative adversarial networks (GANs) are innovative techniques for learning generative models of complex data distributions from samples. Despite remarkable recent improvements in generating realistic images, one of their major shortcomings is the fact that in practice, they tend to produce samples with little diversity, even when trained on diverse datasets. This phenomenon, known as mode collapse, has been the main focus of several recent advances in GANs. Yet there is little understanding of why mode collapse happens and why existing approaches are able to mitigate mode collapse. We propose a principled approach to handling mode collapse, which we call packing. The main idea is to modify the discriminator to make decisions based on multiple samples from the same class, either real or artificially generated. We borrow analysis tools from binary hypothesis testing---in particular the seminal result of Blackwell [Bla53]---to prove a fundamental connection between packing and mode collapse. We show that packing naturally penalizes generators with mode collapse, thereby favoring generator distributions with less mode collapse during the training process. Numerical experiments on benchmark datasets suggests that packing provides significant improvements in practice as well.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

fjxmlzn/PacGAN officialmentioned in papermentioned on GitHubtf report
alex98chen/testGAN mentioned on GitHubtf report
bhargavajs07/Packed_WGAN_GP_Example mentioned on GitHubpytorch report
fjxmlzn/DoppelGANger mentioned on GitHubtf report
xwshen51/AGE mentioned on GitHubpytorch report
xwshen51/AGES mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityTwo-sample testingVocal Bursts Valence Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections