Research map / Label-efficient and robust learning / Domain adaptation and generalization
Gradual Domain Adaptation without Indexed Intermediate Domains
Hong-You Chen, Wei-Lun Chao
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 cycle-consistency refinement to progressive domain discriminator scores (ablation) | IDOL · Rotated MNIST | target accuracy: 85.7 -> 87.5 | Improved |
| add cycle-consistency refinement to progressive domain discriminator scores (ablation) | IDOL · Portraits | target accuracy: 83.4 -> 85.5 | Improved |
| add refinement to pre-defined index sequences (ablation) | GDA · Rotated MNIST | target accuracy: 87.9 -> 93.3 | Improved |
| add refinement to random sequences (ablation) | GDA · Rotated MNIST | target accuracy: 39.5 -> 57.5 | Improved |
| use progressive domain discriminator instead of classifier confidence as coarse score (ablation) | IDOL · Rotated MNIST | target accuracy: 45.5 -> 85.7 | Improved |
| make domain discriminator progressive (ablation) | IDOL · Rotated MNIST | target accuracy: 82.1 -> 85.7 | Improved |
| use IDOL sequence instead of random sequence | GDA · Rotated MNIST | target accuracy: 39.5 -> 87.5 | Improved |
| use IDOL sequence instead of pre-defined years | GDA · Portraits | target accuracy: 85.8 -> 85.5 | No clear effect |
| add IDOL to outlier-domain sequence | GDA · Rotated MNIST outlier domains | target accuracy: 77.0 -> 81.3 | Improved |
| use IDOL instead of confidence-based GDA | GDA · CIFAR10-STL | target accuracy: 77.1 -> 78.1 | Improved |
| use UDA self-training on target plus intermediate data vs source only | UDA · CIFAR10-STL | target accuracy: 76.6 -> 61.1 | Hurt |
Closest papers by meaning
- Gradient-Based Sample Selection for Black-Box Universal Domain Adaptation (AAAI 2025 · similarity 0.88)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.88)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.88)
- Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation (NeurIPS 2025 · similarity 0.88)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.87)
- A Separation and Alignment Framework for Black-Box Domain Adaptation (AAAI 2024 · 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.
