Papers › Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring...
Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator
Yuxuan Song, Qiwei Ye, Minkai Xu, Tie-Yan Liu
Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. The learning objective of GANs usually minimizes some measure discrepancy, \textit{e.g.}, f-divergence~(f-GANs) or Integral Probability Metric~(Wasserstein GANs). With f-divergence as the objective function, the discriminator essentially estimates the density ratio, and the estimated ratio proves useful in further improving the sample quality of the generator. However, how to leverage the information contained in the discriminator of Wasserstein GANs (WGAN) is less explored. In this paper, we introduce the Discriminator Contrastive Divergence, which is well motivated by the property of WGAN's discriminator and the relationship between WGAN and energy-based model. Compared to standard GANs, where the generator is directly utilized to obtain new samples, our method proposes a semi-amortized generation procedure where the samples are produced with the generator's output as an initial state. Then several steps of Langevin dynamics are conducted using the gradient of the discriminator. We demonstrate the benefits of significant improved generation on both synthetic data and several real-world image generation benchmarks.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Generation | CIFAR-10 | SNGAN-DCD (Latent) | FID | 16.24 | #47 of 78 | Archive leaderboard | report |
| Image Generation | CIFAR-10 | SNGAN-DCD (Pixel) | FID | 21.67 | #57 of 78 | Archive leaderboard | report |
| Image Generation | STL-10 | SNGAN-DCD (Latent) | FID | 17.68 | #13 of 31 | Archive leaderboard | report |
| Image Generation | STL-10 | SNGAN-DCD (Latent) | Inception score | 9.33 | #13 of 31 | Archive leaderboard | report |
| Image Generation | STL-10 | SNGAN-DCD (Pixel) | FID | 22.25 | #17 of 31 | Archive leaderboard | report |
| Image Generation | STL-10 | SNGAN-DCD (Pixel) | Inception score | 9.25 | #17 of 31 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
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