Research map / Label-efficient and robust learning / Domain adaptation and generalization
CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency
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 |
|---|---|---|---|
| Add cross-domain consistency loss (ablation) | CrDoCo with DRN-26 · GTA5 → Cityscapes val | mean IoU: 39.4 -> 45.1 | Helped |
| Add cross-domain consistency loss (ablation) | CrDoCo with DRN-26 · GTA5 → Cityscapes val | Pixel acc.: 85.8 -> 89.2 | Helped |
| Add cross-domain consistency loss (ablation) | CrDoCo with DRN-26 · SYNTHIA → Cityscapes val | mean IoU: 29.8 -> 33.4 | Helped |
| Add cross-domain consistency loss (ablation) | CrDoCo with ResNet-50 · Cityscapes → Rome | mean IoU: 51.0 -> 55.1 | Helped |
| Add cross-domain consistency loss (ablation) | CrDoCo with ResNet-50 · Cityscapes → Rio | mean IoU: 48.9 -> 50.4 | Helped |
| Add cross-domain consistency loss (ablation) | CrDoCo with ResNet-50 · Cityscapes → Tokyo | mean IoU: 45.9 -> 51.2 | Helped |
| Add cross-domain consistency loss (ablation) | CrDoCo with ResNet-50 · Cityscapes → Taipei | mean IoU: 46.8 -> 47.9 | Helped |
| Add cross-domain consistency loss (ablation) | CrDoCo · SUNCG → NYUv2 | Abs. Rel.: 0.254 -> 0.233 | Helped |
| Add cross-domain consistency loss (ablation) | CrDoCo with PWC-Net · MPI Sintel clean → KITTI 2012 test | AEPE: 4.92 -> 3.16 | Helped |
| Add cross-domain consistency loss (ablation) | CrDoCo with PWC-Net · MPI Sintel clean → KITTI 2015 test | F1-all: 36.43% -> 25.83% | Helped |
Closest papers by meaning
- Unsupervised Pixel-Level Domain Adaptation With Generative Adversarial Networks (CVPR 2017 · similarity 0.91)
- Image to Image Translation for Domain Adaptation (CVPR 2018 · similarity 0.91)
- PixMatch: Unsupervised Domain Adaptation via Pixelwise Consistency Training (CVPR 2021 · similarity 0.90)
- Learning From Synthetic Data: Addressing Domain Shift for Semantic Segmentation (CVPR 2018 · similarity 0.90)
- Joint Adversarial Learning for Domain Adaptation in Semantic Segmentation (AAAI 2020 · similarity 0.90)
- Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation (CVPR 2019 · similarity 0.89)
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.