Research map / Label-efficient and robust learning / Domain adaptation and generalization
Collaborative Optimization and Aggregation for Decentralized Domain Generalization and Adaptation
Guile Wu, Shaogang Gong
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 hybrid batch-instance normalization (ablation) | COPA · PACS | accuracy: 82.6 -> 85.1 | Improved |
| add collaboration of frozen classifiers (ablation) | COPA · PACS | accuracy: 82.7 -> 85.1 | Improved |
| add iterative optimization and aggregation (ablation) | COPA · PACS | accuracy: 79.6 -> 85.1 | Improved |
| add iteration, HBIN and CoFC together (ablation) | COPA · PACS | accuracy: 69.7 -> 85.1 | Improved |
| replace FedAvg parameter averaging with feature-extractor aggregation plus classifier ensemble | decentralized backbone · PACS | accuracy: 77.9 -> 85.1 | Improved |
| replace independent training plus logit ensemble with COPA | Ind-Ensemble · PACS | accuracy: 70.6 -> 85.1 | Improved |
| replace centralized joint training with decentralized COPA | Backbone · PACS | accuracy: 79.5 -> 85.1 | Improved |
| replace centralized joint training with decentralized COPA | Backbone · Digits-DG | accuracy: 73.7 -> 81.5 | Improved |
| use RandAugment inside CoFC (ablation) | COPA · PACS | accuracy | Improved |
| replace hybrid BN-IN with instance normalization only (ablation) | COPA · PACS | accuracy | Hurt |
| replace HBIN with IBN-a/IBN-b (ablation) | COPA · PACS | accuracy | Hurt |
| replace HBIN with Switchable Norm (ablation) | COPA · PACS | accuracy | No clear effect |
Closest papers by meaning
- Domain Aggregation Networks for Multi-Source Domain Adaptation (ICML 2020 · similarity 0.88)
- Federated Domain Generalization with Data-free On-server Matching Gradient (ICLR 2025 · similarity 0.88)
- Unknown Domain Inconsistency Minimization for Domain Generalization (ICLR 2024 · similarity 0.87)
- Multi-Source Collaborative Gradient Discrepancy Minimization for Federated Domain Generalization (AAAI 2024 · similarity 0.87)
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.86)
- One-Step Generalization Ratio Guided Optimization for Domain Generalization (ICML 2025 · 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.
