Research map / Architectures and efficiency / Mixture of experts
Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs
Yikang Zhang, Zhuo Chen, Zhao Zhong
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 CoE expert collaboration to OFA-230 | OFA-230 · ImageNet validation | Top-1 accuracy: 78.0% to 80.7% | Improved |
| Add CondConv to CoE-Large | CoE-Large · ImageNet validation | Top-1 accuracy: 80.7% -> 81.5% | Improved |
| Replace gate-value routing with CoE's label-supervised training | OFA-230 with four experts · ImageNet validation | Top-1 accuracy: 78.7% -> 79.9%; 78.9% -> 79.9% | Improved |
| Replace category-based routing with learned CoE selection | OFA-230 with four experts · ImageNet validation | Top-1 accuracy: 78.3% -> 79.9%; 77.5% -> 79.9% | Improved |
| Add model-level CoE instead of averaging four model predictions | OFA-230 · ImageNet validation | Top-1 accuracy: 79.6% -> 80.7% | Improved |
| Add LGM for expert selection (ablation) | CoE-Large · ImageNet validation | Top-1 accuracy: 78.0% -> 79.9% | Improved |
| Add WGM to assign weighted training portions to experts (ablation) | CoE-Large · ImageNet validation | Top-1 accuracy: 78.1% -> 79.9% | Improved |
| Partition training data by delegator output rather than expert suitability (ablation) | CoE-Large WGM · ImageNet validation | Top-1 accuracy: 77.0% -> 79.9% | Improved |
| Add suitability standardization and equal-expert assignment constraint (ablation) | CoE-Large LGM · ImageNet validation | Top-1 accuracy: 79.4% -> 79.9% | Improved |
| Add equal assignment and smoothing in WGM (ablation) | CoE-Large WGM · ImageNet validation | Top-1 accuracy: 79.2% -> 79.9% | Improved |
| Use progressive rather than constant assignment sharpening (ablation) | CoE-Large WGM · ImageNet validation | Top-1 accuracy: 79.4% -> 79.9% | Improved |
| Reweight expert-selection loss by sample suitability differences (ablation) | CoE-Large · ImageNet validation | Top-1 accuracy: 79.5% -> 79.9% | Improved |
Closest papers by meaning
- A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts (ICML 2024 · similarity 0.86)
- Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks (CVPR 2025 · similarity 0.85)
- Mixture of Nested Experts: Adaptive Processing of Visual Tokens (NeurIPS 2024 · similarity 0.85)
- Tight Clusters Make Specialized Experts (ICLR 2025 · similarity 0.85)
- DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models (CVPR 2025 · similarity 0.85)
- Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization (NeurIPS 2024 · similarity 0.85)
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.
