2 citations · 3 across the 10 of their papers we have counts for
3 papers · 1 filter
On Unsupervised Partial Shape Correspondence
Amit Bracha, Thomas Dagès, Ron Kimmel
While dealing with matching shapes to their parts, we often apply a tool known as functional maps. The idea is to translate the shape matching problem into "convenient" spaces by w…
A model is worth tens of thousands of examples
Thomas Dagès, Laurent D. Cohen, Alfred M. Bruckstein
Traditional signal processing methods relying on mathematical data generation models have been cast aside in favour of deep neural networks, which require vast amounts of data. Sin…
From Compass and Ruler to Convolution and Nonlinearity: On the Surprising Difficulty of Understanding a Simple CNN Solving a Simple Geometric Estimation Task
Thomas Dagès, Michael Lindenbaum, Alfred M. Bruckstein
Neural networks are omnipresent, but remain poorly understood. Their increasing complexity and use in critical systems raises the important challenge to full interpretability. We p…