Research map / Label-efficient and robust learning / Domain adaptation and generalization
Multi-Source Domain Adaptation With Collaborative Learning for 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 |
|---|---|---|---|
| Add LAB-based image translation (ablation) | Direct Transfer on GTA5 · Cityscapes val | mIoU: 39.53 -> 43.36 | Helped |
| Add LAB-based image translation (ablation) | AdaptSeg on GTA5 · Cityscapes val | mIoU: 41.32 -> 43.66 | Helped |
| Add LAB-based image translation (ablation) | AdaptSeg-LS on GTA5 · Cityscapes val | mIoU: 43.11 -> 45.95 | Helped |
| Add LAB-based image translation (ablation) | Advent on GTA5 · Cityscapes val | mIoU: 44.30 -> 45.96 | Helped |
| Add LAB-based image translation to combined-source training (ablation) | GTA5 + Synscapes adaptation · Cityscapes val | mIoU: 51.59 -> 54.38 | Helped |
| Add source collaborative learning (ablation) | LAB-translated combined-source adaptation · Cityscapes val | mIoU: 54.38 -> 56.03 | Helped |
| Add target collaborative learning (ablation) | LAB-translated combined-source adaptation · Cityscapes val | mIoU: 54.38 -> 54.03 | Helped |
| Add source collaborative learning (ablation) | LAB translation plus target collaborative learning · Cityscapes val | mIoU: 54.03 -> 58.55 | Helped |
| Add target collaborative learning (ablation) | LAB translation plus source collaborative learning · Cityscapes val | mIoU: 56.03 -> 58.55 | Helped |
| Add LAB-based translation (ablation) | Source and target collaborative learning · Cityscapes val | mIoU: 57.27 -> 58.55 | Helped |
| Ensemble source-specific model predictions (ablation) | Proposed method · Cityscapes val (GTA5 + Synscapes) | mIoU: 56.90 -> 58.55; 56.65 -> 58.55 | Helped |
| Use stage-wise rather than end-to-end training (ablation) | Full proposed method · Cityscapes val (GTA5 + Synscapes) | mIoU: 58.6 -> 59.0 | Helped |
Closest papers by meaning
- Multi-Target Domain Adaptation With Collaborative Consistency Learning (CVPR 2021 · similarity 0.95)
- Source-Free Domain Adaptation for Semantic Segmentation (CVPR 2021 · similarity 0.93)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.91)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.90)
- Open-Set Domain Adaptation for Semantic Segmentation (CVPR 2024 · 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.