Research map / Label-efficient and robust learning / Domain adaptation and generalization
DINO: A Conditional Energy-Based GAN for Domain Translation
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 L1 reconstruction loss (ablation) | DINO · CelebAMask-HQ | PSNR: 11.34 -> 12.08 | Helped |
| add L1 reconstruction loss (ablation) | DINO · CelebAMask-HQ | SSIM: 0.36 -> 0.38 | Helped |
| add L1 reconstruction loss (ablation) | DINO · CelebAMask-HQ | FID: 69.9 -> 51.5 | Helped |
| add adaptive balancing rather than using a fixed margin (ablation) | DINO without L1 · CelebAMask-HQ | FID: 89.5 -> 69.9 | Helped |
| add adaptive balancing rather than using a fixed margin (ablation) | DINO without L1 · CelebAMask-HQ | mIoU: 58.8 % -> 69.4 % | Helped |
| use bidirectional training | DINO · CelebAMask-HQ | PSNR: 12.08 -> 12.18 | Helped |
| use bidirectional training | DINO · Cityscapes | PSNR: 16.44 -> 16.78 | Helped |
| use predictive conditioning through reverse reconstruction | DINO · GRID unseen subjects video→speech | WER: 40.5 % -> 32.6 % | Helped |
| use predictive conditioning through reverse reconstruction | DINO · GRID unseen subjects video→speech | STOI: 0.45 -> 0.51 | Helped |
Closest papers by meaning
- Learning to Transfer: Unsupervised Domain Translation via Meta-Learning (AAAI 2020 · similarity 0.90)
- Conditional Image-to-Image Translation (CVPR 2018 · similarity 0.89)
- Image-to-image translation for cross-domain disentanglement (NeurIPS 2018 · similarity 0.87)
- Unsupervised Image-to-Image Translation With Generative Prior (CVPR 2022 · similarity 0.87)
- HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks (NeurIPS 2022 · similarity 0.87)
- Network-to-Network Translation with Conditional Invertible Neural Networks (NeurIPS 2020 · 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.