Research map / Label-efficient and robust learning / Domain adaptation and generalization
SSF-DAN: Separated Semantic Feature Based Domain Adaptation Network for Semantic Segmentation
Liang Du, Jingang Tan, Hongye Yang, Jianfeng Feng, Xiangyang Xue, Qibao Zheng, Xiaoqing Ye, Xiaolin Zhang
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 SS-D (independent class-wise adaptation) without progressive confidence in place of soft class-wise alignment with global (ablation) | soft class-wise + global · GTA5 to Cityscapes | mIoU: 40.2 -> 42.8 | Improved |
| add global alignment to SS-D dagger (ablation) | SS-D dagger · GTA5 to Cityscapes | mIoU: 42.8 -> 42.6 | No clear effect |
| add progressive confidence strategy (ablation) | SS-D dagger · GTA5 to Cityscapes | mIoU: 42.8 -> 44.0 | Improved |
| add CA-R class-wise adversarial loss reweighting (ablation) | SS-D · GTA5 to Cityscapes | mIoU: 44.0 -> 45.4 | Improved |
| add global feature alignment alone (ablation) | source only · GTA5 to Cityscapes | mIoU: 36.6 -> 39.3 | Improved |
| add soft class-wise alignment alone (ablation) | source only · GTA5 to Cityscapes | mIoU: 36.6 -> 38.0 | Improved |
| add SSF-DAN adaptation | source only DeepLab-v2 · Synthia to Cityscapes | mIoU: 38.6 -> 50.0 | Improved |
Closest papers by meaning
- Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features (TPAMI 2021 · similarity 0.90)
- FDA: Fourier Domain Adaptation for Semantic Segmentation (CVPR 2020 · similarity 0.90)
- SemiDAViL: Semi-supervised Domain Adaptation with Vision-Language Guidance for Semantic Segmentation (CVPR 2025 · similarity 0.90)
- Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training (ECCV 2018 · similarity 0.89)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 2025 · similarity 0.88)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 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.
