Research map / Label-efficient and robust learning / Domain adaptation and generalization
DaDA: Distortion-aware Domain Adaptation for Unsupervised Semantic Segmentation
Sujin Jang, Joohan Na, Dokwan Oh
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 RA+RDL distortion-aware transformation | AdvEnt · Cityscapes->Woodscape | mIoU (%): 45.26 -> 52.64 | Improved |
| add RA+RDL distortion-aware transformation | AdaptSeg · Cityscapes->Woodscape | mIoU (%): 46.33 -> 52.59 | Improved |
| add RA+RDL distortion-aware transformation | AdvEnt · GTAV->Woodscape | mIoU (%): 34.70 -> 37.62 | Improved |
| add RA+RDL distortion-aware transformation | AdvEnt · GTAV->FDD | mIoU (%): 37.25 -> 40.87 | Improved |
| add only RandAugment affine transformation (ablation) | AdaptSeg · GTAV->Woodscape | mIoU (%): 35.94 -> 36.88 | Improved |
| add only diffeomorphic RDL (ablation) | AdaptSeg · Cityscapes->FDD | mIoU (%): 39.07 -> 41.35 | Improved |
| add RA on top of RDL (ablation) | AdaptSeg+RDL · Cityscapes->FDD | mIoU (%): 41.35 -> 41.07 | Hurt |
| add RA on top of RDL (ablation) | AdvEnt+RDL · Cityscapes->FDD | mIoU (%): 42.43 -> 42.32 | Hurt |
| add RA on top of RDL (ablation) | AdvEnt+RDL · GTAV->Woodscape | mIoU (%): 36.39 -> 37.62 | Improved |
| use DaDA as warm-up for IAST | IAST · Cityscapes->Woodscape | mIoU (%): 47.00 -> 53.82 | Improved |
| use DaDA as warm-up for IntraDA | IntraDA · GTAV->Woodscape | mIoU (%): 36.10 -> 39.85 | Improved |
| use DaDA as warm-up for ProDA | ProDA · GTAV->FDD | mIoU (%): 35.97 -> 37.09 | Improved |
Closest papers by meaning
- DADA: Depth-Aware Domain Adaptation in Semantic Segmentation (ICCV 2019 · similarity 0.91)
- Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation (ICCV 2023 · similarity 0.90)
- I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation (TPAMI 2022 · similarity 0.89)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.89)
- Open-Set Domain Adaptation for Semantic Segmentation (CVPR 2024 · similarity 0.88)
- Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation (NeurIPS 2025 · similarity 0.88)
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.
