Research map / Label-efficient and robust learning / Domain adaptation and generalization
Self-Adversarial Disentangling for Specific Domain Adaptation
Qianyu Zhou, Qiqi Gu, Jiangmiao Pang, Xuequan Lu, Lizhuang Ma
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 Domainness Creator (ablation) | GPA · Cityscapes to Foggy Cityscapes (VGG16) | mAP: 39.5 -> 42.5 | Improved |
| add Self-Adversarial Regularizer after DC (ablation) | GPA + DC · Cityscapes to Foggy Cityscapes | mAP: 42.5 -> 45.2 | Improved |
| add DC to AdaptSegNet (ablation) | AdaptSegNet · Foggy Zurich++ segmentation (mIoU) | mAP: 29.4 -> 33.5 | Improved |
| add SAR after DC (ablation) | AdaptSegNet + DC · Foggy Zurich++ segmentation (mIoU) | mAP: 33.5 -> 35.2 | Improved |
| use DC instead of random crop augmentation (ablation) | GPA · Cityscapes to Foggy Cityscapes | mAP: 42.7 -> 45.2 | Improved |
| use DC instead of color jittering augmentation (ablation) | GPA · Cityscapes to Foggy Cityscapes | mAP: 41.8 -> 45.2 | Improved |
| add L_inv alongside L_spf (ablation) | GPA + DC · Cityscapes to Foggy Cityscapes | mAP: 43.1 -> 45.2 | Improved |
| add L_spf alongside L_inv (ablation) | GPA + DC · Cityscapes to Foggy Cityscapes | mAP: 43.3 -> 45.2 | Improved |
| use SAR instead of MRL (ablation) | AdaptSegNet + DC · Foggy Zurich++ segmentation (mIoU) | mAP: 34.0 -> 35.2 | Improved |
| use SAR instead of CIDA (ablation) | AdaptSegNet + DC · Foggy Zurich++ segmentation (mIoU) | mAP: 34.2 -> 35.2 | Improved |
| increase domainness number N from 0 to 4 (ablation) | Ours · Virtual KITTI to CKITTI | mAP: 46.14 -> 50.57 | Improved |
| increase domainness number N from 0 to 4 (ablation) | Ours · Cityscapes to RainCityscapes | mAP: 34.96 -> 44.21 | Improved |
Closest papers by meaning
- Adversarial-Learned Loss for Domain Adaptation (AAAI 2020 · similarity 0.89)
- Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation (ICCV 2023 · similarity 0.89)
- Partial Adversarial Domain Adaptation (ECCV 2018 · similarity 0.89)
- An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation (AAAI 2020 · similarity 0.89)
- Bridging Theory and Algorithm for Domain Adaptation (ICML 2019 · similarity 0.88)
- Toward Improving Robustness and Accuracy in Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.87)
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.
