Research map / Label-efficient and robust learning / Domain adaptation and generalization
Multi-Anchor Active Domain Adaptation for Semantic Segmentation
Munan Ning, Donghuan Lu, Dong Wei, Cheng Bian, Chenglang Yuan, Shuang Yu, Kai Ma, Yefeng Zheng
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 active samples with cross-entropy loss (ablation) | adversarial DA baseline · GTA5->Cityscapes | mIoU: 42.5 -> 61.6 | Improved |
| add active samples with cross-entropy loss (ablation) | adversarial DA baseline · SYNTHIA->Cityscapes | mIoU: 42.9 -> 65.0 | Improved |
| add multi-anchor soft alignment loss (ablation) | MADA · GTA5->Cityscapes | mIoU: 61.6 -> 63.2 | Improved |
| add multi-anchor soft alignment loss (ablation) | MADA · SYNTHIA->Cityscapes | mIoU: 65.0 -> 66.6 | Improved |
| update target anchors with EMA (ablation) | MADA · GTA5->Cityscapes | mIoU: 63.2 -> 63.8 | Improved |
| update target anchors with EMA (ablation) | MADA · SYNTHIA->Cityscapes | mIoU: 66.6 -> 67.6 | Improved |
| add pseudo label loss on unlabeled target (ablation) | MADA · GTA5->Cityscapes | mIoU: 63.8 -> 64.9 | Improved |
| add pseudo label loss on unlabeled target (ablation) | MADA · SYNTHIA->Cityscapes | mIoU: 67.6 -> 68.1 | Improved |
| multi-anchor selection instead of AADA selection | active learning · GTA5->Cityscapes | mIoU: 59.3 -> 61.6 | Improved |
| multi-anchor selection instead of random selection | active learning · GTA5->Cityscapes | mIoU: 56.7 -> 61.6 | Improved |
| increase active sample fraction from 1% to 20% (ablation) | MADA · GTA5->Cityscapes | mIoU: 56.7 -> 64.1 | Improved |
| use K-means instead of spectral clustering (ablation) | MADA · GTA5->Cityscapes | mIoU: 61.02 -> 61.58 | Improved |
Closest papers by meaning
- MADAv2: Advanced Multi-Anchor Based Active Domain Adaptation Segmentation (TPAMI 2023 · similarity 0.94)
- Learning to Adapt via Latent Domains for Adaptive Semantic Segmentation (NeurIPS 2021 · similarity 0.91)
- D2ADA: Dynamic Density-Aware Active Domain Adaptation for Semantic Segmentation (ECCV 2022 · similarity 0.91)
- Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation (NeurIPS 2019 · similarity 0.90)
- Density Matters: Improved Core-Set for Active Domain Adaptive Segmentation (AAAI 2024 · 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.
