Papers › Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs
Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs
Yikang Zhang, Zhuo Chen, Zhao Zhong
In this paper, we propose a Collaboration of Experts (CoE) framework to pool together the expertise of multiple networks towards a common aim. Each expert is an individual network with expertise on a unique portion of the dataset, which enhances the collective capacity. Given a sample, an expert is selected by the delegator, which simultaneously outputs a rough prediction to support early termination. To fulfill this framework, we propose three modules to impel each model to play its role, namely weight generation module (WGM), label generation module (LGM) and variance calculation module (VCM). Our method achieves the state-of-the-art performance on ImageNet, 80.7% top-1 accuracy with 194M FLOPs. Combined with PWLU activation function and CondConv, CoE further achieves the accuracy of 80.0% with only 100M FLOPs for the first time. More importantly, our method is hardware friendly and achieves a 3-6x speedup compared with some existing conditional computation approaches.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Classification | ImageNet | CoE-Large + CondConv | GFLOPs | 0.214 | #629 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | CoE-Large + CondConv | Top 1 Accuracy | 81.5% | #629 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | CoE-Large | GFLOPs | 0.194 | #686 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | CoE-Large | Number of params | 95.3M | #686 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | CoE-Large | Top 1 Accuracy | 80.7% | #686 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | CoE-Small + CondConv + PWLU | GFLOPs | 0.100 | #722 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | CoE-Small + CondConv + PWLU | Top 1 Accuracy | 80% | #722 of 1060 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections