Research map / Label-efficient and robust learning / Domain adaptation and generalization
FREDOM: Fairness Domain Adaptation Approach to Semantic Scene Understanding
Read the paperCheck 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 L_Class to the adapted model (ablation) | FREDOM with DeepLab-V2 · SYNTHIA → Cityscapes | mIoU: 56.1 -> 57.0 | Helped |
| add L_Class to the adapted model (ablation) | FREDOM with DeepLab-V2 · GTA5 → Cityscapes | mIoU: 57.4 -> 59.2 | Helped |
| add L_Cond alongside L_Class (ablation) | FREDOM with DeepLab-V2 · SYNTHIA → Cityscapes | mIoU: 57.0 -> 59.1 | Helped |
| add L_Cond alongside L_Class (ablation) | FREDOM with DeepLab-V2 · GTA5 → Cityscapes | mIoU: 59.2 -> 61.3 | Helped |
| add L_Class to the adapted model (ablation) | FREDOM with DeepLab-V2 · SYNTHIA → Cityscapes | IoU STD: 25.3 -> 24.9 | Helped |
| add L_Cond alongside L_Class (ablation) | FREDOM with DeepLab-V2 · SYNTHIA → Cityscapes | IoU STD: 24.9 -> 24.0 | Helped |
| add L_Class to the adapted model (ablation) | FREDOM with DeepLab-V2 · GTA5 → Cityscapes | IoU STD: 20.9 -> 19.8 | Helped |
| add L_Cond alongside L_Class (ablation) | FREDOM with DeepLab-V2 · GTA5 → Cityscapes | IoU STD: 19.8 -> 19.1 | Helped |
| use a Transformer backbone instead of DeepLab-V2 | FREDOM · SYNTHIA → Cityscapes | mIoU: 59.1 -> 67.0 | Helped |
| use a Transformer backbone instead of DeepLab-V2 | FREDOM · GTA5 → Cityscapes | mIoU: 61.3 -> 73.6 | Helped |
| use FREDOM instead of DAFormer with the same Transformer backbone | Transformer-based UDA · SYNTHIA → Cityscapes | mIoU: 60.9 -> 67.0 | Helped |
| use FREDOM instead of DAFormer with the same Transformer backbone | Transformer-based UDA · GTA5 → Cityscapes | mIoU: 68.3 -> 73.6 | Helped |
Closest papers by meaning
- On the Road to Online Adaptation for Semantic Image Segmentation (CVPR 2022 · similarity 0.88)
- Multi-source Domain Adaptation for Semantic Segmentation (NeurIPS 2019 · similarity 0.87)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · similarity 0.86)
- Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation (NeurIPS 2020 · similarity 0.86)
- FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding (CVPR 2025 · similarity 0.86)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.85)
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.