Research map / Image generation / GANs
Global Versus Localized 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 LGAN for semi-supervised classification instead of the strongest listed baseline | Semi-supervised classifier · SVHN, 500 labels | classification error: 7.05$\pm$0.30 -> 5.48 $\pm$ 0.29 | Helped |
| Use LGAN for semi-supervised classification instead of the strongest listed baseline | Semi-supervised classifier · SVHN, 1,000 labels | classification error: 5.43$\pm$0.25 -> 4.73 $\pm$ 0.16 | Helped |
| Use LGAN for semi-supervised classification instead of the strongest listed baseline | Semi-supervised classifier · CIFAR-10, 1,000 labels | classification error: 19.98 $\pm$ 0.89 -> 17.44 $\pm$ 0.25 | Helped |
| Use LGAN for semi-supervised classification instead of the strongest listed baseline | Semi-supervised classifier · CIFAR-10, 4,000 labels | classification error: 14.87 -> 14.23 $\pm$ 0.27 | Helped |
| Use LGAN with Conv-Large instead of the strongest listed baseline | Semi-supervised classifier · CIFAR-10, 4,000 labels | classification error: $10.55$ -> $\mathbf{9.77 \pm 0.13}$ | Helped |
| Use LGAN with Conv-Large instead of the strongest listed baseline | Semi-supervised classifier · CIFAR-100, 10,000 labels | classification error: $38.65 \pm 0.51$ -> $\mathbf{35.52 \pm 0.33}$ | Helped |
| Sample more than ten local coordinates per minibatch when computing the orthonormality-prior errors (ablation) | LGAN · SVHN and CIFAR-10 | classification accuracy | No clear effect |
Closest papers by meaning
- Manifold Learning Benefits GANs (CVPR 2022 · similarity 0.91)
- A Geometric Analysis of Deep Generative Image Models and Its Applications (ICLR 2021 · similarity 0.90)
- Improving GAN with Neighbors Embedding and Gradient Matching (AAAI 2019 · similarity 0.89)
- Disconnected Manifold Learning for Generative Adversarial Networks (NeurIPS 2018 · similarity 0.89)
- Geometry Score: A Method For Comparing Generative Adversarial Networks (ICML 2018 · similarity 0.87)
- SMaRt: Improving GANs with Score Matching Regularity (ICML 2024 · 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.