Research map / Label-efficient and robust learning / Domain adaptation and generalization
Exemplar Guided Unsupervised Image-to-Image Translation with Semantic Consistency
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 exemplar-guided AdaIN and feature masks with perceptual loss | EGSC-IT · MNIST-Single A→B | SSIM: 0.214±0.168 (CycleGAN), 0.178±0.160 (UNIT), 0.463±0.094 (MUNIT), 0.478 ± 0.090 (EGSC-IT) | Helped |
| add exemplar-guided AdaIN and feature masks with perceptual loss | EGSC-IT · MNIST-Single B→A | SSIM: 0.232 ± 0.131 vs 0.227±0.128 | No clear effect |
| add feature masks (ablation) | EGSC-IT · MNIST-Single A→B | SSIM: 0.395±0.137 -> 0.478 ± 0.090 | Helped |
| add feature masks (ablation) | EGSC-IT · MNIST-Single B→A | SSIM: 0.133±0.171 -> 0.232 ± 0.131 | Helped |
| add AdaIN (ablation) | EGSC-IT · MNIST-Single A→B | SSIM: 0.208±0.166 -> 0.478 ± 0.090 | Helped |
| add AdaIN (ablation) | EGSC-IT · MNIST-Single B→A | SSIM: 0.080±0.167 -> 0.232 ± 0.131 | Mixed |
| add perceptual loss (ablation) | EGSC-IT · MNIST-Single A→B | SSIM: 0.286±0.183 -> 0.478 ± 0.090 | Helped |
| add perceptual loss (ablation) | EGSC-IT · MNIST-Single B→A | SSIM: 0.093±0.169 -> 0.232 ± 0.131 | Helped |
| translate GTA5 images using EGSC-IT rather than source images without translation | DeepLab trained on translated images · GTA5→BDD | mIoU: 0.329 -> 0.343 | Helped |
| use EGSC-IT rather than MUNIT for translation | DeepLab trained on translated images · GTA5→BDD | mIoU: 0.331 -> 0.343 | Helped |
Closest papers by meaning
- Cross-Domain Correspondence Learning for Exemplar-Based Image Translation (CVPR 2020 · similarity 0.92)
- Masked and Adaptive Transformer for Exemplar Based Image Translation (CVPR 2023 · similarity 0.90)
- Image-To-Image Translation via Group-Wise Deep Whitening-And-Coloring Transformation (CVPR 2019 · similarity 0.90)
- Unbalanced Feature Transport for Exemplar-Based Image Translation (CVPR 2021 · similarity 0.89)
- SynthRGB-T: Language-Vision Guided Image Translation for Diversity Synthesis (CVPR 2026 · similarity 0.87)
- Learning to Manipulate Artistic Images (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.