Research map / Learning theory and algorithms / Kernels and regression theory
Kernel of CycleGAN as a principal homogeneous space
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 |
|---|---|---|---|
| Add identity loss with weight 10.0 instead of 0.0 (ablation) | CycleGAN · BRATS2015 | Loss: 0.83 -> 0.46 | Helped |
| Add identity loss with weight 10.0 instead of 0.0 (ablation) | CycleGAN · BRATS2015 | PSNR T1-Fl: 23.8 -> 24.6 | Helped |
| Increase identity-loss weight from 10.0 to 40.0 (ablation) | CycleGAN · BRATS2015 | Loss: 0.46 -> 3.36 | Hurt |
| Increase identity-loss weight from 0.0 to 40.0 (ablation) | CycleGAN · BRATS2015 | PSNR T1-Fl: 23.8 -> 24.6 | No clear effect |
| Increase identity-loss weight (ablation) | CycleGAN · BRATS2015 | symmetry under horizontal flips | Helped |
| Train on a domain translated to itself rather than assuming the learned mapping is the identity | CycleGAN · MNIST2MNIST | digit-class preservation | Hurt |
Closest papers by meaning
- On Translation and Reconstruction Guarantees of the Cycle-Consistent Generative Adversarial Networks (NeurIPS 2022 · similarity 0.89)
- Guiding the One-to-One Mapping in CycleGAN via Optimal Transport (AAAI 2019 · similarity 0.86)
- Breaking the Cycle - Colleagues Are All You Need (CVPR 2020 · similarity 0.85)
- On Making $SE(2)$-Invariant Networks Optimal (NeurIPS 2026 · similarity 0.83)
- Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold (AAAI 2024 · similarity 0.83)
- StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation (CVPR 2024 · similarity 0.83)
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.