Research map / Label-efficient and robust learning / Domain adaptation and generalization
Phase Consistent Ecological Domain Adaptation
Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano Soatto
AI-extracted. The measured effects below were read by AI from the paper's full text (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 the scene compatibility prior (ablation) | ResNet-101 segmentation model · GTA5-to-Cityscapes | mIoU: 44.3 -> 45.3 | Improved |
| add the scene compatibility prior (ablation) | ResNet-101 segmentation model with self-supervised learning · GTA5-to-Cityscapes | mIoU: 47.6 -> 49.7 | Improved |
| add the scene compatibility prior (ablation) | VGG-16 segmentation model · GTA5-to-Cityscapes | mIoU: 37.7 -> 40.9 | Improved |
| add the scene compatibility prior (ablation) | VGG-16 segmentation model with self-supervised learning · GTA5-to-Cityscapes | mIoU: 41.3 -> 43.1 | Improved |
| add the scene compatibility prior (ablation) | DRN-26 segmentation model · GTA5-to-Cityscapes | mIoU: 39.5 -> 41.7 | Improved |
| add phase consistency to the image transformation (ablation) | UDA semantic segmentation · GTA5-to-Cityscapes | mIoU: 44.8 -> 45.3 | Improved |
| use output-space regularization (ablation) | UDA semantic segmentation · GTA5-to-Cityscapes | mIoU: 45.3 -> 44.8 | Hurt |
| add the proposed domain adaptation method | ResNet-101 segmentation model · GTA5-to-Cityscapes | mIoU: 48.5 -> 50.5 | Improved |
| add the proposed domain adaptation method | VGG-16 segmentation model · GTA5-to-Cityscapes | mIoU: 41.3 -> 44.6 | Improved |
| add the proposed domain adaptation method | ResNet-101 segmentation model · Synthia-to-Cityscapes | mIoU*: 51.4 -> 53.6 | Improved |
| add the proposed domain adaptation method | VGG-16 segmentation model · Synthia-to-Cityscapes | mIoU*: 46.1 -> 48.7 | Improved |
Closest papers by meaning
- Unsupervised Model Adaptation for Continual Semantic Segmentation (AAAI 2021 · similarity 0.91)
- Generalize Then Adapt: Source-Free Domain Adaptive Semantic Segmentation (ICCV 2021 · similarity 0.90)
- On the Road to Online Adaptation for Semantic Image Segmentation (CVPR 2022 · similarity 0.90)
- FDA: Fourier Domain Adaptation for Semantic Segmentation (CVPR 2020 · similarity 0.90)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.89)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · 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.
