Research map / Label-efficient and robust learning / Domain adaptation and generalization
All About Structure: Adapting Structural Information Across Domains for Boosting Semantic 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 DISE instead of the strongest reported baseline, Hong et al. | GTA5-to-Cityscapes semantic segmentation · GTA5 to Cityscapes val | mIoU: 44.5 -> 45.4 | Helped |
| Use DISE instead of the strongest reported baseline, Tsai et al. | SYNTHIA-to-Cityscapes semantic segmentation · SYNTHIA to Cityscapes val (16 classes) | mIoU: 40.0 -> 41.5 | Helped |
| Add output-space domain adversarial alignment (ablation) | Source-only segmentation model · GTA5 to Cityscapes val | mIoU: 39.8 -> 42.6 | Helped |
| Add structure-texture disentanglement and image-translation losses (ablation) | Seg-map Adaptation · GTA5 to Cityscapes val | mIoU: 42.6 -> 44.1 | Helped |
| Add label-transfer loss on translated source images (ablation) | DISE without label transfer · GTA5 to Cityscapes val | mIoU: 44.1 -> 45.4 | Helped |
Closest papers by meaning
- Addressing Domain Gap via Content Invariant Representation for Semantic Segmentation (AAAI 2021 · similarity 0.92)
- Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation (CVPR 2020 · similarity 0.91)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Open-Set Domain Adaptation for Semantic Segmentation (CVPR 2024 · similarity 0.90)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.89)
- Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation (NeurIPS 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.