Research map / Label-efficient and robust learning / Domain adaptation and generalization
Compound Domain Generalization via Meta-Knowledge Encoding
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 COMEN instead of MixStyle | PACS domain generalization · PACS | average accuracy: 83.7 -> 85.7 | Helped |
| Use COMEN instead of SFA-A | Digits-DG domain generalization · Digits-DG | average accuracy: 79.6 -> 82.3 | Helped |
| Use COMEN instead of MASF | VLCS domain generalization · VLCS | average accuracy: 74.1 -> 75.0 | Helped |
| Use COMEN instead of L2A-OT | Office-Home domain generalization · Office-Home | average accuracy: 65.6 -> 66.5 | Helped |
| Add DSNorm to the DeepAll baseline (ablation) | COMEN framework · PACS | accuracy: 79.1 -> 81.3 | Helped |
| Add ProtoGR to the DeepAll baseline (ablation) | COMEN framework · PACS | accuracy: 79.1 -> 82.0 | Helped |
| Add ProtoCCL to the DeepAll baseline (ablation) | COMEN framework · PACS | accuracy: 79.1 -> 81.3 | Helped |
| Add ProtoGR and ProtoCCL without DSNorm (ablation) | COMEN framework · PACS | accuracy: 79.1 -> 82.6 | Helped |
| Add DSNorm and ProtoGR without ProtoCCL (ablation) | COMEN framework · PACS | accuracy: 79.1 -> 83.5 | Helped |
| Add DSNorm and ProtoCCL without ProtoGR (ablation) | COMEN framework · PACS | accuracy: 79.1 -> 84.0 | Helped |
| Add DSNorm, ProtoGR, and ProtoCCL (ablation) | COMEN framework · PACS | accuracy: 79.1 -> 85.7 | Helped |
Closest papers by meaning
- Exploiting Domain-Specific Features to Enhance Domain Generalization (NeurIPS 2021 · similarity 0.92)
- Towards Generalizing to Unseen Domains with Few Labels (CVPR 2024 · similarity 0.90)
- Unknown Domain Inconsistency Minimization for Domain Generalization (ICLR 2024 · similarity 0.88)
- Improving Domain Generalization with Domain Relations (ICLR 2024 · similarity 0.88)
- Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler (NeurIPS 2024 · similarity 0.88)
- Reasoning-Driven Multimodal LLM for Domain Generalization (ICLR 2026 · 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.