Research map / Label-efficient and robust learning / Domain adaptation and generalization
A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
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 |
|---|---|---|---|
| Use UFDN rather than StarGAN | CelebA image translation · Sketch→Photo | SSIM: 0.8026 -> 0.8222 | Helped |
| Use UFDN rather than StarGAN | CelebA image translation · Paint→Photo | SSIM: 0.8496 -> 0.8798 | Helped |
| Use UFDN rather than the strongest listed baseline | UFDN · MNIST→USPS | accuracy: 95.97 -> 97.13 | Helped |
| Use UFDN rather than the strongest listed baseline | UFDN · USPS→MNIST | accuracy: 94.35 -> 93.77 | Hurt |
| Use UFDN rather than the strongest listed baseline | UFDN · SVHN→MNIST | accuracy: 92.40 -> 95.01 | Helped |
| Add self-supervised feature disentanglement with D_v (ablation) | UFDN · Multi-domain image translation | domain-controlled translation | Helped |
| Add pixel-space adversarial learning (ablation) | UFDN · Multi-domain image translation | domain distinction in generated images | Helped |
Closest papers by meaning
- Image-to-image translation for cross-domain disentanglement (NeurIPS 2018 · similarity 0.93)
- Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation (CVPR 2018 · similarity 0.92)
- Multi-mapping Image-to-Image Translation via Learning Disentanglement (NeurIPS 2019 · similarity 0.90)
- Fix the Noise: Disentangling Source Feature for Controllable Domain Translation (CVPR 2023 · similarity 0.89)
- Domain Agnostic Learning with Disentangled Representations (ICML 2019 · similarity 0.89)
- Disentangled Prompt Representation for Domain Generalization (CVPR 2024 · similarity 0.86)
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.