Research map / Label-efficient and robust learning / Domain adaptation and generalization
Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation
Geon Lee, Chanho Eom, Wonkyung Lee, Hyekang Park, Bumsub Ham
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 forward contrastive loss (FCL) aligning prototypes and pixel features across domains to the static-label baseline (ablation) | Bi-directional contrastive DASS · GTA5/SYNTHIA -> Cityscapes val | mIoU | Improved |
| jointly optimize both contrastive terms (bi-directional) rather than one (ablation) | Bi-directional contrastive DASS · GTA5/SYNTHIA -> Cityscapes val | mIoU | Improved |
| add dynamic pseudo labels on top of static ones, without calibration (ablation) | Bi-directional contrastive DASS · GTA5/SYNTHIA -> Cityscapes val | mIoU | Improved |
| add class-wise calibration of source prototypes (ablation) | Bi-directional contrastive DASS · GTA5/SYNTHIA -> Cityscapes val | mIoU | Improved |
| use instance-wise prototypes instead of momentum-based prototypes for pseudo labels (ablation) | Bi-directional contrastive DASS · GTA5 -> Cityscapes | mIoU | Improved |
| use proposed method instead of ProDA (same architecture) | Ours vs ProDA · GTA5 -> Cityscapes | mIoU: 0.6% mIoU gain | Improved |
| use proposed method instead of ProDA (same architecture) | Ours vs ProDA · SYNTHIA -> Cityscapes | mIoU: 1.6% mIoU gain | Improved |
Closest papers by meaning
- Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation (ECCV 2022 · similarity 0.93)
- Weakly-Supervised Domain Adaptive Semantic Segmentation With Prototypical Contrastive Learning (CVPR 2023 · similarity 0.93)
- SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation (TPAMI 2023 · similarity 0.92)
- Open-Set Domain Adaptation for Semantic Segmentation (CVPR 2024 · similarity 0.91)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.91)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.90)
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.
