Research map / Image generation / Editing and style transfer
Breaking the Cycle - Colleagues Are All You Need
Check 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 cycle-consistency translation with collaborative council training | Council-GAN · CelebA male-to-female | FID: 19.88 -> 18.85 | Helped |
| Replace cycle-consistency translation with collaborative council training | Council-GAN · CelebA male-to-female | KID: 0.0012 -> 0.0010 | Helped |
| Replace cycle-consistency translation with collaborative council training | Council-GAN · selfie2anime | FID: 109.22 -> 101.39 | Helped |
| Replace cycle-consistency translation with collaborative council training | Council-GAN · selfie2anime | KID: 0.0020 -> 0.0020 | No clear effect |
| Replace cycle-consistency translation with collaborative council training | Council-GAN · CelebA glasses removal | FID: 50.72 -> 36.38 | Helped |
| Replace cycle-consistency translation with collaborative council training | Council-GAN · CelebA glasses removal | KID: 0.0038 -> 0.0026 | Helped |
| Add Council_loss to GAN_loss (ablation) | Council-GAN · CelebA male-to-female | input-output face relatedness | Helped |
| Add Focus_loss to GAN_loss (ablation) | Council-GAN · CelebA male-to-female | input-output face relatedness | Hurt |
| Add Focus_loss to GAN_loss (ablation) | Council-GAN · CelebA male-to-female | background preservation | Helped |
| Combine Council_loss and Focus_loss (ablation) | Council-GAN · CelebA male-to-female | joint face relatedness and background focus | Helped |
| Use fewer council members (ablation) | Council-GAN · CelebA male-to-female | accuracy | Hurt |
| Train for more iterations (ablation) | Council-GAN · CelebA male-to-female | KID | Helped |
Closest papers by meaning
- TraVeLGAN: Image-To-Image Translation by Transformation Vector Learning (CVPR 2019 · similarity 0.91)
- On Translation and Reconstruction Guarantees of the Cycle-Consistent Generative Adversarial Networks (NeurIPS 2022 · similarity 0.90)
- Polymorphic-GAN: Generating Aligned Samples Across Multiple Domains With Learned Morph Maps (CVPR 2022 · similarity 0.89)
- Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping (CVPR 2019 · similarity 0.88)
- Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translation (AAAI 2024 · similarity 0.87)
- Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold (AAAI 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.