Research map / Label-efficient and robust learning / Domain adaptation and generalization
Cross-Domain Collaborative Normalization via Structural Knowledge
Read the paperCheck 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 |
|---|---|---|---|
| Replace BN with CoN | CDAN, ResNet-50 · Image-CLEF (average) | classification accuracy (%): 87.7 -> 90.3 | Helped |
| Replace TN with CoN | CDAN, ResNet-50 · Image-CLEF (average) | classification accuracy (%): 88.5 -> 90.3 | Helped |
| Replace BN with CoN | CDAN, ResNet-50 · Office-31 (average) | classification accuracy (%): 87.7 -> 90.3 | Helped |
| Replace TN with CoN | CDAN, ResNet-50 · Office-31 (average) | classification accuracy (%): 89.3 -> 90.3 | Helped |
| Replace BN with CoN | CDAN, ResNet-50 · Office-Home (average) | classification accuracy (%): 65.8 -> 68.7 | Helped |
| Replace TN with CoN | CDAN, ResNet-50 · Office-Home (average) | classification accuracy (%): 67.6 -> 68.7 | Helped |
| Replace BN with CoN | CDAN, ResNet-50 · Office-Home Cl→Ar | classification accuracy (%): 57.6 -> 63.6 | Helped |
| Replace BN with CoN | CDAN, ResNet-50 · Office-Home Cl→Pr | classification accuracy (%): 70.0 -> 74.3 | Helped |
| Replace BN with CoN | CDAN, ResNet-50 · Office-31 D→W | classification accuracy (%): 98.6 -> 98.4 | Hurt |
| Replace BN with CoN | CDAN, ResNet-50 · Office-Home Rw→Cl | classification accuracy (%): 56.7 -> 55.6 | Hurt |
| Use CoN instead of BN or TN | CDAN · Image-CLEF P→I and C→P | iterations to reach optimal classification accuracy: 2,000; 3,500; 4,500 | Helped |
Closest papers by meaning
- Domain-Specific Batch Normalization for Unsupervised Domain Adaptation (CVPR 2019 · similarity 0.92)
- Reducing Divergence in Batch Normalization for Domain Adaptation (AAAI 2025 · similarity 0.92)
- MetaNorm: Learning to Normalize Few-Shot Batches Across Domains (ICLR 2021 · similarity 0.89)
- Leveraging Normalization Layer in Adapters with Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning (AAAI 2024 · similarity 0.88)
- Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization (AAAI 2024 · similarity 0.87)
- Domain-Aware Fine-Tuning: Enhancing Neural Network Adaptability (AAAI 2024 · similarity 0.86)
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.