Research map / Label-efficient and robust learning / Recognition and long-tail
Learning GANs and Ensembles Using Discrepancy
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 |
|---|---|---|---|
| Optimize mixture weights across pretrained generators with discrepancy | CIFAR10 ensembles evaluated with InceptionLogits · CIFAR10, InceptionLogits | discrepancy: 259.61 -> 255.3 | Helped |
| Optimize mixture weights across pretrained generators with discrepancy | CIFAR10 ensembles evaluated with InceptionPool · CIFAR10, InceptionPool | discrepancy: 64.37 -> 63.98 | Helped |
| Optimize mixture weights across pretrained generators with discrepancy | CIFAR10 ensembles evaluated with MobileNet · CIFAR10, MobileNet | discrepancy: 88.01 -> 81.83 | Helped |
| Optimize mixture weights across pretrained generators with discrepancy | CIFAR10 ensembles evaluated with PNASNet · CIFAR10, PNASNet | discrepancy: 34.38 -> 33.97 | Helped |
| Optimize mixture weights across pretrained generators with discrepancy | CIFAR10 ensembles evaluated with NASNet · CIFAR10, NASNet | discrepancy: 52.66 -> 52.46 | Helped |
| Optimize mixture weights across pretrained generators with discrepancy | CIFAR10 ensembles evaluated with AmoebaNet · CIFAR10, AmoebaNet | discrepancy: 97.71 -> 97.71 | No clear effect |
Closest papers by meaning
- Improving Generalization and Stability of Generative Adversarial Networks (ICLR 2019 · similarity 0.92)
- On the Discrimination-Generalization Tradeoff in GANs (ICLR 2018 · similarity 0.91)
- Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy (ICLR 2017 · similarity 0.91)
- Training Generative Adversarial Networks with Limited Data (NeurIPS 2020 · similarity 0.90)
- Chi-square Generative Adversarial Network (ICML 2018 · similarity 0.90)
- Discriminative Forests Improve Generative Diversity for Generative Adversarial Networks (AAAI 2024 · similarity 0.89)
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.