Research map / Label-efficient and robust learning / Domain adaptation and generalization
CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation
Jiahua Dong, Yang Cong, Gan Sun, Yuyang Liu, Xiaowei Xu
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 the transferability-critic based adversarial framework (ablation) | CSCL · GTA to Cityscapes (VGG-16) | mIoU: 39.6 -> 41.4 | Improved |
| add the confidence-guided pseudo label generator (ablation) | CSCL · GTA to Cityscapes (VGG-16) | mIoU: 39.2 -> 41.4 | Improved |
| add the symmetric soft divergence loss (ablation) | CSCL · GTA to Cityscapes (VGG-16) | mIoU: 40.4 -> 41.4 | Improved |
| add the transferability-critic based adversarial framework (ablation) | CSCL · GTA to Cityscapes (ResNet-101) | mIoU: 46.7 -> 48.6 | Improved |
| add the confidence-guided pseudo label generator (ablation) | CSCL · GTA to Cityscapes (ResNet-101) | mIoU: 46.1 -> 48.6 | Improved |
| add the symmetric soft divergence loss (ablation) | CSCL · GTA to Cityscapes (ResNet-101) | mIoU: 47.4 -> 48.6 | Improved |
| add the transferability-critic based adversarial framework (ablation) | CSCL · SYNTHIA to Cityscapes (VGG-16) | mIoU: 38.1 -> 39.2 | Improved |
| add the confidence-guided pseudo label generator (ablation) | CSCL · SYNTHIA to Cityscapes (VGG-16) | mIoU: 37.0 -> 39.2 | Improved |
| add the symmetric soft divergence loss (ablation) | CSCL · SYNTHIA to Cityscapes (VGG-16) | mIoU: 38.6 -> 39.2 | Improved |
| add the transferability-critic based adversarial framework (ablation) | CSCL · SYNTHIA to Cityscapes (ResNet-101) | mIoU: 45.4 -> 47.2 | Improved |
| add the confidence-guided pseudo label generator (ablation) | CSCL · SYNTHIA to Cityscapes (ResNet-101) | mIoU: 44.3 -> 47.2 | Improved |
| add the symmetric soft divergence loss (ablation) | CSCL · SYNTHIA to Cityscapes (ResNet-101) | mIoU: 46.0 -> 47.2 | Improved |
Closest papers by meaning
- Category-Level Adversarial Adaptation for Semantic Segmentation using Purified Features (TPAMI 2021 · similarity 0.90)
- Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation (CVPR 2019 · similarity 0.90)
- CrDoCo: Pixel-Level Domain Transfer With Cross-Domain Consistency (CVPR 2019 · similarity 0.90)
- Unsupervised Model Adaptation for Continual Semantic Segmentation (AAAI 2021 · similarity 0.89)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.88)
- Universal Domain Adaptation for Semantic Segmentation (CVPR 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.
