Researchers from Carnegie Mellon University, the University of Texas at Austin and Facebook AI propose a novel paradigm to optimize widths for each CNN layer. The method is compatible across various width optimization algorithms and networks and achieves up to a 320x reduction in width optimization overhead without compromising top-1 accuracy on ImageNet.

Here is a quick read: CMU, UT Austin & Facebook’s CNN Layer Width Optimization Strategies Achieve 320x Overhead Reduction.

The paper Width Transfer: On the (In)Variance of Width Optimization is on arXiv.



Source link