Research map / Label-efficient and robust learning / Domain adaptation and generalization
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
Yang Zhang, Philip David, Boqing Gong
Read the paperCheck your idea against 137,217 papers
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 curriculum with image-level label distribution (ablation) | NoAdapt · GTA -> Cityscapes | mean IoU: 22.3 -> 23.1 | Improved |
| add superpixel label-distribution constraint (ablation) | NoAdapt · GTA -> Cityscapes | mean IoU: 22.3 -> 27.8 | Improved |
| combine image-level and superpixel label distributions (ablation) | Ours (SP) · GTA -> Cityscapes | mean IoU: 27.8 -> 28.9 | Improved |
| combine image-level and superpixel label distributions (ablation) | Ours (I) · GTA -> Cityscapes | mean IoU: 23.1 -> 28.9 | Improved |
| curriculum adaptation vs prior superpixel baseline | SP · GTA -> Cityscapes | mean IoU: 26.8 -> 28.9 | Improved |
| curriculum adaptation vs FCN in the Wild | FCN Wld · GTA -> Cityscapes | mean IoU: 27.1 -> 28.9 | Improved |
Closest papers by meaning
- A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes (TPAMI 2019 · similarity 0.92)
- Crots: Cross-Domain Teacher–Student Learning for Source-Free Domain Adaptive Semantic Segmentation (IJCV 2023 · similarity 0.89)
- Constructing Self-Motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach (ICCV 2019 · similarity 0.87)
- Stronger Fewer & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentation (CVPR 2024 · similarity 0.85)
- Learning Content-Enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentation (AAAI 2024 · similarity 0.85)
- Open-Set Domain Adaptation for Semantic Segmentation (CVPR 2024 · similarity 0.84)
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.
