Research map / Image generation / GANs
Improved Training of Generative Adversarial Networks Using Representative Features
Duhyeon Bang, Hyunjung Shim
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Add representative features from a pretrained autoencoder | DCGAN · CelebA | MS-SSIM: 0.4432 -> 0.4038 | Improved |
| Add representative features from a pretrained autoencoder | LSGAN · CelebA | MS-SSIM: 0.3907 -> 0.3770 | Improved |
| Add representative features from a pretrained autoencoder | DRAGAN · CelebA | MS-SSIM: 0.3869 -> 0.3683 | Improved |
| Add representative features from a pretrained autoencoder | WGAN-GP · CelebA | MS-SSIM: 0.3813 -> 0.3773 | Improved |
| Add representative features from a pretrained autoencoder | DCGAN and LSGAN · CIFAR-10 | Inception score: +0.128 mean improvement | Improved |
| Add representative features from a pretrained autoencoder | DRAGAN and WGAN-GP · CIFAR-10 | Inception score | Mixed |
| Replace the encoder convolution layer with a residual block (ablation) | DCGAN-RF · CIFAR-10 | Inception score: 6.64 -> 6.73 | Improved |
Closest papers by meaning
- Stabilizing Training of Generative Adversarial Networks through Regularization (NeurIPS 2017 · similarity 0.90)
- Progressive Growing of GANs for Improved Quality, Stability, and Variation (ICLR 2018 · similarity 0.89)
- On Stabilizing Generative Adversarial Training With Noise (CVPR 2019 · similarity 0.88)
- Progressive Augmentation of GANs (NeurIPS 2019 · similarity 0.88)
- Improving Generalization and Stability of Generative Adversarial Networks (ICLR 2019 · similarity 0.88)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.87)
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.
