Search Results for author:
Found 2 papers, 1 papers with code
Neighbourhood Distillation: On the benefits of non end-to-end distillation
Instead of distilling a model end-to-end, we propose to split it into smaller sub-networks - also called neighbourhoods - that are then trained independently.
Fine-Grained Stochastic Architecture Search
Mobile neural architecture search (NAS) methods automate the design of small models but state-of-the-art NAS methods are expensive to run.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
