Research map / Image generation / Editing and style transfer
Domain Adaptive Image-to-Image Translation
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 |
|---|---|---|---|
| Adapt the source-domain StarGAN with DAI2I | StarGAN on stylized CelebA · Stylized CelebA, Smiling | ACC (%): 15.3 -> 96.1 | Helped |
| Adapt the source-domain StarGAN with DAI2I | StarGAN on stylized CelebA · Stylized CelebA, Mustache | FID: 178.9 -> 14.2 | Helped |
| Adapt StarGAN with DAI2I | StarGAN on sketch expression manipulation · Sketch | expression recognition (%): 26.3 -> 68.7 | Helped |
| Adapt StarGAN with DAI2I | StarGAN on painting expression manipulation · Painting | expression recognition (%): 30.7 -> 55.1 | Helped |
| Adapt StarGAN with DAI2I | StarGAN on cat-face expression manipulation · Cat faces | expression recognition (%): 22.9 -> 43.0 | Helped |
| Add adaptation loss LADA (ablation) | DAI2I · Stylized CelebA, Smiling | ACC (%): 0.2 -> 96.1 | Helped |
| Add reconstruction loss Lrec (ablation) | DAI2I · Stylized CelebA, Smiling | FID: 41.9 -> 14.9 | Helped |
| Add perceptual analogy loss LPA (ablation) | DAI2I · Stylized CelebA, Smiling | ACC (%): 15.3 -> 96.1 | Helped |
| Add domain-specific batch normalization for feature calibration (ablation) | DAI2I · Stylized CelebA, Smiling | FID: 41.4 -> 14.9 | Helped |
| Add AdaIN style adaptation (ablation) | DAI2I · Stylized CelebA, Smiling | FID: 18.5 -> 14.9 | Helped |
| Increase the analogy-loss scale α (ablation) | DAI2I · Stylized CelebA | visual output quality | Hurt |
| Add an adversarial loss on the reconstructor output in target domain B (ablation) | DAI2I · Out-of-domain image translation | target-attribute modification | Hurt |
Closest papers by meaning
- Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation (CVPR 2021 · similarity 0.89)
- Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation (CVPR 2022 · similarity 0.89)
- Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint (CVPR 2022 · similarity 0.88)
- Benign Examples: Imperceptible Changes Can Enhance Image Translation Performance (AAAI 2020 · similarity 0.88)
- Rethinking the Paradigm of Content Constraints in Unpaired Image-to-Image Translation (AAAI 2024 · similarity 0.87)
- Deterministic Image-to-Image Translation via Denoising Brownian Bridge Models with Dual Approximators (CVPR 2025 · 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.