49 citations · 131 across the 10 of their papers we have counts for
14 papers
Finsler Multi-Dimensional Scaling: Manifold Learning for Asymmetric Dimensionality Reduction and Embedding
Thomas Dagès, Simon Weber, Ya-Wei Eileen Lin +5
Dimensionality reduction is a fundamental task that aims to simplify complex data by reducing its feature dimensionality while preserving essential patterns, with core applications…
Metric Convolutions: A Unifying Theory to Adaptive Image Convolutions
Thomas Dagès, Michael Lindenbaum, Alfred M. Bruckstein
Standard convolutions are prevalent in image processing and deep learning, but their fixed kernels limits adaptability. Several deformation strategies of the reference kernel grid…
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…
Assessing hierarchies by their consistent segmentations
Zeev Gutman, Ritvik Vij, Laurent Najman +1
Current approaches to generic segmentation start by creating a hierarchy of nested image partitions and then specifying a segmentation from it. Our first contribution is to describ…
On the Minimal Recognizable Image Patch
Mark Fonaryov, Michael Lindenbaum
In contrast to human vision, common recognition algorithms often fail on partially occluded images. We propose characterizing, empirically, the algorithmic limits by finding a mini…
DPDist : Comparing Point Clouds Using Deep Point Cloud Distance
Dahlia Urbach, Yizhak Ben-Shabat, Michael Lindenbaum
We introduce a new deep learning method for point cloud comparison. Our approach, named Deep Point Cloud Distance (DPDist), measures the distance between the points in one cloud an…