Research map / Image generation / GANs
EigenGAN: Layer-Wise Eigen-Learning for GANs
Zhenliang He, Meina Kan, Shiguang Shan
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 layer-wise subspace models (ablation) | EigenGAN generator · CelebA face generation, role of layer-wise latent variables | share of major variation captured by layer-wise latents | Improved |
| add bottom noise besides layer-wise latents | EigenGAN generator · CelebA face generation | captured variation | Improved |
| increase data rank from 5 to 20 (subspace rank 5 or more) | Linear EigenGAN · toy datasets, Gaussian data | cosine similarity with PCA: 1.00 -> 0.78 (KL-f-GAN, 5→1 vs 20→5) | Hurt |
| change GAN loss among KL-f-GAN, Vanilla, WGAN, LSGAN, Hinge | Linear EigenGAN · toy datasets | cosine similarity with PCA: 0.99 -> 1.00 (10→1, WGAN vs Vanilla GAN) | No clear effect |
| change data distribution from Gaussian to uniform | Linear EigenGAN · toy datasets, 20→1 KL-f-GAN | cosine similarity with PCA: 0.97 -> 0.89 | Hurt |
| change data distribution from Gaussian to uniform | Linear EigenGAN · toy datasets, 10→3 WGAN | cosine similarity with PCA: 0.89 -> 0.93 | No clear effect |
Closest papers by meaning
- Interpreting the Latent Space of GANs for Semantic Face Editing (CVPR 2020 · similarity 0.88)
- Linear Semantics in Generative Adversarial Networks (CVPR 2021 · similarity 0.87)
- InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs (TPAMI 2020 · similarity 0.87)
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (NeurIPS 2016 · similarity 0.87)
- Energy-based Generative Adversarial Networks (ICLR 2017 · similarity 0.86)
- Closed-Form Factorization of Latent Semantics in GANs (CVPR 2021 · similarity 0.86)
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.
