Research map / Label-efficient and robust learning / Domain adaptation and generalization
Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation
Check 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 |
|---|---|---|---|
| Use CLAN's category-adaptive adversarial loss instead of TAN's global adversarial loss | VGG16-FCN8s · GTA5 → Cityscapes | mIoU: 35.0 -> 36.6 | Helped |
| Use CLAN's category-adaptive adversarial loss instead of TAN's global adversarial loss | ResNet101 · GTA5 → Cityscapes | mIoU: 41.4 -> 43.2 | Helped |
| Use CLAN's category-adaptive adversarial loss instead of TAN's global adversarial loss | VGG16-FCN8s · SYNTHIA → Cityscapes | mIoU: 37.6 -> 39.3 | Helped |
| Use CLAN's category-adaptive adversarial loss instead of TAN's global adversarial loss | ResNet101 · SYNTHIA → Cityscapes | mIoU: 45.9 -> 47.8 | Helped |
| Add category-adaptive adversarial loss to source-only segmentation | CLAN with VGG16-FCN8s · GTA5 → Cityscapes | mIoU: +18.7% | Helped |
| Add category-adaptive adversarial loss to source-only segmentation | CLAN with ResNet101 · SYNTHIA → Cityscapes | mIoU: 9.2% | Helped |
| Set ε very small (0.1 or 0.2) (ablation) | CLAN · Domain-adaptation parameter study | discriminator-loss convergence | Hurt |
| Vary λ_local over {10, 20, 40, 80} with ε = 0.4 (ablation) | CLAN · Domain-adaptation parameter study | discriminator-loss convergence | No clear effect |
| Use λ_local = 40 and ε = 0.4 (ablation) | CLAN · Domain-adaptation parameter study | adaptation performance | Helped |
Closest papers by meaning
- An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation (AAAI 2020 · similarity 0.94)
- Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation (NeurIPS 2019 · similarity 0.92)
- Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation (CVPR 2020 · similarity 0.92)
- Coarse-To-Fine Domain Adaptive Semantic Segmentation With Photometric Alignment and Category-Center Regularization (CVPR 2021 · similarity 0.91)
- Balanced Learning for Domain Adaptive Semantic Segmentation (ICML 2025 · similarity 0.89)
- 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.