no code implementations • 23 Apr 2023 • Shay Dekel, Yosi Keller, Aharon Bar-Hillel
We propose a novel formulation of deep networks that do not use dot-product neurons and rely on a hierarchy of voting tables instead, denoted as Convolutional Tables (CT), to enable accelerated CPU-based inference.
no code implementations • 27 Sep 2018 • Yuval Litvak, Armin Biess, Aharon Bar-Hillel
We obtain an average pose estimation error of 2. 16 millimeters and 0. 64 degree leading to 91% success rate for robotic assembly of randomly distributed parts.
no code implementations • 14 Feb 2016 • Aharon Bar-Hillel, Eyal Krupka, Noam Bloom
We study classifiers operating under severe classification time constraints, corresponding to 1-1000 CPU microseconds, using Convolutional Tables Ensemble (CTE), an inherently fast architecture for object category recognition.
no code implementations • CVPR 2013 • Dan Levi, Shai Silberstein, Aharon Bar-Hillel
Our algorithm is an accelerated version of the "Feature Synthesis" (FS) method [1], which uses multiple object parts for detection and is among state-of-theart methods on human detection benchmarks, but also suffers from a high computational cost.