Research map / Image generation / GANs
Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training
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 |
|---|---|---|---|
| Replace Gaussian latent input with a closely related image dataset | Spider DCGAN · MNIST | FID: 21.49 -> 16.80 | Helped |
| Use TinyImageNet images instead of Gaussian latent input | Spider DCGAN · CIFAR-10 | FID: 71.84 -> 58.82 | Helped |
| Use Fashion MNIST images as generator input | Spider DCGAN · CIFAR-10 | FID: 71.84 -> 77.86 | Hurt |
| Use CelebA images instead of Gaussian latent input | Spider DCGAN · Ukiyo-E Faces | FID: 62.26 -> 54.09 | Helped |
| Use Fashion MNIST images as generator input | Spider DCGAN · Ukiyo-E Faces | FID: 62.26 -> 72.431 | Hurt |
| Replace Gaussian input with TinyImageNet input | Spider PGGAN · Ukiyo-E Faces | FID: 69.03 -> 57.63 | Helped |
| Replace Gaussian input with TinyImageNet input | Spider PGGAN · MetFaces | FID: 85.74 -> 45.32 | Helped |
| Use TinyImageNet images as input | Spider StyleGAN2 · Ukiyo-E Faces | FID: 26.74 -> 20.44 | Helped |
| Use TinyImageNet images as input | Spider StyleGAN2 · MetFaces | FID: 18.75 -> 15.60 | Helped |
| Use AFHQ-Dogs images instead of TinyImageNet images as input | Spider StyleGAN2 · MetFaces | FID: 15.60 -> 29.82 | Hurt |
| Use TinyImageNet images as input | Spider StyleGAN2-ADA · FFHQ | FID: 2.70 -> 2.45 | Helped |
| Use Tiny-ImageNet input with AFHQ-Dogs weight transfer | Spider StyleGAN2-ADA · AFHQ-Cats | FID: 3.47 -> 3.07 | Helped |
Closest papers by meaning
- Improving GAN with Neighbors Embedding and Gradient Matching (AAAI 2019 · similarity 0.90)
- Instance-Conditioned GAN (NeurIPS 2021 · similarity 0.90)
- Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration (CVPR 2023 · similarity 0.89)
- RG-GAN: Dynamic Regenerative Pruning for Data-Efficient Generative Adversarial Networks (AAAI 2024 · similarity 0.89)
- The GAN is dead; long live the GAN! A Modern GAN Baseline (NeurIPS 2024 · similarity 0.89)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · 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.