Research map / Image generation / GANs
Dual Discriminator Generative Adversarial Nets
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use D2GAN instead of GAN | GAN · MNIST-1K | modes covered: 628.0±140.9 -> 1000.0±0.00 | Helped |
| Use D2GAN instead of GAN | GAN · MNIST-1K | reverse KL divergence: 2.58±0.75 -> 0.08±0.01 | Helped |
| Use D2GAN instead of UnrolledGAN | UnrolledGAN · MNIST-1K | modes covered: 817.4±37.9 -> 1000.0±0.00 | Helped |
| Use D2GAN instead of UnrolledGAN | UnrolledGAN · MNIST-1K | reverse KL divergence: 1.43±0.12 -> 0.08±0.01 | Helped |
| Use D2GAN instead of DCGAN | DCGAN · MNIST-1K | modes covered: 849.6±62.7 -> 1000.0±0.00 | Helped |
| Use D2GAN instead of DCGAN | DCGAN · MNIST-1K | reverse KL divergence: 0.73±0.09 -> 0.08±0.01 | Helped |
| Use D2GAN instead of Reg-GAN | Reg-GAN · MNIST-1K | modes covered: 955.5±18.7 -> 1000.0±0.00 | Helped |
| Use D2GAN instead of Reg-GAN | Reg-GAN · MNIST-1K | reverse KL divergence: 0.64±0.05 -> 0.08±0.01 | Helped |
| Increase β with α fixed, up to a suitable value (ablation) | D2GAN · MNIST | MODE score | Mixed |
| Increase network size (ablation) | D2GAN · MNIST | MODE score | No clear effect |
| Use DFM instead of D2GAN | D2GAN · CIFAR-10, STL-10, and ImageNet | Inception score | Helped |
Closest papers by meaning
- MGAN: Training Generative Adversarial Nets with Multiple Generators (ICLR 2018 · similarity 0.92)
- MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators (NeurIPS 2022 · similarity 0.92)
- Dualing GANs (NeurIPS 2017 · similarity 0.92)
- Mixed batches and symmetric discriminators for GAN training (ICML 2018 · similarity 0.91)
- TRAINING GENERATIVE ADVERSARIAL NETWORKS VIA PRIMAL-DUAL SUBGRADIENT METHODS: A LAGRANGIAN PERSPECTIVE ON GAN (ICLR 2018 · similarity 0.91)
- Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator (ICML 2025 · similarity 0.90)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.