Alapfogalmak
SlimSAM introduces a novel data-efficient compression method for Segment Anything Model (SAM) that achieves superior performance with minimal training data.
Statisztikák
SlimSAM achieves approaching performance while reducing parameter counts to merely 1.4% (9.1M), MACs to 0.8% (23G), and requiring only 0.1% (10k) of the SAM training data.