Search Results for author:
Found 4 papers, 0 papers with code
Deep Convolutional Tables: Deep Learning without Convolutions
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.
Learning Pose Estimation for High-Precision Robotic Assembly Using Simulated Depth Images
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.
Convolutional Tables Ensemble: classification in microseconds
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.
Fast Multiple-Part Based Object Detection Using KD-Ferns
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.
