Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts

Neural Information Processing Systems 

We generate a set of diverse expert models via hypernetworks to cover all possible distribution scenarios, and optimize the model ensemble to adapt to any test distribution. Crucially, in any distribution scenario, we can flexibly output a dedicated model solution that matches the user's preference.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found