Papers › RankGAN: A Maximum Margin Ranking GAN for Generating Faces

RankGAN: A Maximum Margin Ranking GAN for Generating Faces

19 Dec 2018arXiv:1812.08196archive 2025-07-28

Rahul Dey, Felix Juefei-Xu, Vishnu Naresh Boddeti, Marios Savvides

We present a new stage-wise learning paradigm for training generative adversarial networks (GANs). The goal of our work is to progressively strengthen the discriminator and thus, the generators, with each subsequent stage without changing the network architecture. We call this proposed method the RankGAN. We first propose a margin-based loss for the GAN discriminator. We then extend it to a margin-based ranking loss to train the multiple stages of RankGAN. We focus on face images from the CelebA dataset in our work and show visual as well as quantitative improvements in face generation and completion tasks over other GAN approaches, including WGAN and LSGAN.

PaperPDFCode

Code

human-analysis/RankGAN 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

Face Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Batch NormalizationConvolutionDense ConnectionsGAN Least Squares LossLSGANReLUWGAN

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