CMU, UT Austin & Facebook’s CNN Layer Width Optimization Strategies Achieve 320x Overhead Reduction | Synced
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 variou...
Source: Synced | AI Technology & Industry Review
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.