UCSD & Microsoft Improve Image Recognition With Extremely Low FLOPs | Synced
A research team from University of California San Diego and Microsoft proposes Micro-Factorized Convolution (MF-Conv), a novel approach that can deal with extremely low computational costs (4M–21M ...
Source: Synced | AI Technology & Industry Review
A research team from University of California San Diego and Microsoft proposes Micro-Factorized Convolution (MF-Conv), a novel approach that can deal with extremely low computational costs (4M–21M FLOPs) and achieves significant performance gains over state of the art models in the low FLOP regime.