Research map / Label-efficient and robust learning / Domain adaptation and generalization
Semantic-Aware Domain Generalized Segmentation
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 |
|---|---|---|---|
| Use the full method instead of the strongest listed DG baseline | ResNet-50 segmentation model · GTA5 → Cityscapes | mIoU (%): 36.84 -> 39.75 | Helped |
| Use the full method instead of the strongest listed DG baseline | ResNet-50 segmentation model · GTA5 → BDDS | mIoU (%): 35.20 -> 37.34 | Helped |
| Use the full method instead of the strongest listed DG baseline | ResNet-50 segmentation model · GTA5 → Mapillary | mIoU (%): 40.33 -> 41.86 | Helped |
| Use the full method instead of the strongest listed DG baseline | ResNet-50 segmentation model · GTA5 → SYNTHIA | mIoU (%): 28.30 -> 30.79 | Helped |
| Add SAN (ablation) | Baseline segmentation model · GTA5 → Cityscapes, BDDS, Mapillary and SYNTHIA | mIoU (%): + 8.71% average improvement | Helped |
| Add SAW (ablation) | Baseline segmentation model · GTA5 → Cityscapes, BDDS, Mapillary and SYNTHIA | mIoU (%): + 7.93% average improvement | Helped |
| Add SAN and SAW together rather than SAN alone (ablation) | Baseline segmentation model · GTA5 → Cityscapes, BDDS, Mapillary and SYNTHIA | mIoU (%): 38.92, 36.43, 40.11, 28.91 -> 39.75, 37.34, 41.86, 30.79 | Helped |
| Remove CFR from SAN (ablation) | SAN · GTA5 → Cityscapes, BDDS, Mapillary and SYNTHIA | mIoU (%): 38.92 -> 35.51; 36.43 -> 33.24; 40.11 -> 38.68; 28.91 -> 27.76 | Hurt |
| Replace category-related SAW grouping with GIW grouping (ablation) | Whitening module · GTA5 → Cityscapes, BDDS, Mapillary and SYNTHIA | mIoU (%): 37.54, 34.97, 39.85, 28.46 vs 35.76, 32.88, 36.95, 27.24 | Hurt |
| Replace GIW grouping with IW (ablation) | Whitening module · GTA5 → Cityscapes | mIoU (%): 35.76 -> 33.19 | Hurt |
| Set semantic alignment category parameter C to 4 (ablation) | SAN and SAW · GTA5 generalization | mIoU (%): null | Helped |
| Set CFR clustering parameter k to 5 (ablation) | CFR · GTA5 generalization | mIoU (%): null | Helped |
Closest papers by meaning
- Exploring Semantic Consistency and Style Diversity for Domain Generalized Semantic Segmentation (AAAI 2025 · similarity 0.92)
- Collaborating Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.91)
- Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.91)
- A Simple Recipe for Language-guided Domain Generalized Segmentation (CVPR 2024 · similarity 0.90)
- Style Blind Domain Generalized Semantic Segmentation via Covariance Alignment and Semantic Consistence Contrastive Learning (CVPR 2024 · similarity 0.90)
- FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation (CVPR 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.