no code implementations • 12 Mar 2024 • Meir Yossef Levi, Guy Gilboa
We propose a fast and simple explainable AI (XAI) method for point cloud data.
1 code implementation • 30 Dec 2023 • Elnatan Kadar, Guy Gilboa
We propose a new way to explain and to visualize neural network classification through a decomposition-based explainable AI (DXAI).
no code implementations • 20 Dec 2023 • Jonathan Brokman, Roy Betser, Rotem Turjeman, Tom Berkov, Ido Cohen, Guy Gilboa
Our modeling can improve training efficiency and lower communication overhead, as shown by our preliminary experiments in the context of federated learning.
2 code implementations • 10 Aug 2023 • Meir Yossef Levi, Guy Gilboa
In this study, we develop a general mechanism to increase neural network robustness based on focus analysis.
Ranked #1 on Point Cloud Classification on PointCloud-C
no code implementations • 4 May 2023 • Elnatan Kadar, Jonathan Brokman, Guy Gilboa
We present a new model, training procedure and architecture to create precise maps of distinction between two classes of images.
1 code implementation • ICCV 2023 • Meir Yossef Levi, Guy Gilboa
In this work we propose a general ensemble framework, based on partial point cloud sampling.
Ranked #4 on Point Cloud Classification on PointCloud-C
no code implementations • 12 Jan 2023 • Or Streicher, Guy Gilboa
For semi-supervised problems, the common approach is to solve a constrained optimization problem, regularized by a Dirichlet energy, based on the graph-Laplacian.
no code implementations • 18 Dec 2022 • Rotem Turjeman, Tom Berkov, Ido Cohen, Guy Gilboa
We propose in this work a model based on the correlation of the parameters' dynamics, which dramatically reduces the dimensionality.
no code implementations • CVPR 2023 • Or Streicher, Ido Cohen, Guy Gilboa
We analyze the degrees of freedom of learning this task using batches and propose a stable alignment mechanism that can work both with batch changes and with graph-metric changes.
no code implementations • 12 Jun 2022 • Jonathan Brokman, Guy Gilboa
In this work, we present a methodological analysis of Branch Specialization.
1 code implementation • 20 May 2022 • Ilya Tcenov, Guy Gilboa
Given a sampling budget B, a depth predictor P and a desired quality measure M, we propose an Importance Map that highlights important sampling locations.
no code implementations • 21 Nov 2021 • Eyal Gofer, Guy Gilboa
Most notable is the Moore-Penrose inverse, widely used in physics, statistics, and various fields of engineering.
no code implementations • 17 Dec 2020 • Eyal Gofer, Guy Gilboa
In this work we consider a simple feedback model that generalizes both, where on every round, in addition to a bandit feedback, the adversary provides a lower bound on the loss of each expert.
no code implementations • 6 Oct 2020 • Guy Gilboa
In this chapter we are examining several iterative methods for solving nonlinear eigenvalue problems.
1 code implementation • 27 Jul 2020 • Eyal Gofer, Shachar Praisler, Guy Gilboa
Compared with a random or grid sampling pattern, our method allows a reduction by a factor of 4-10 in the number of measurements required to attain the same accuracy.
no code implementations • 3 Jul 2020 • Ido Cohen, Omri Azencot, Pavel Lifshitz, Guy Gilboa
Definitions for spectrum and filtering are given, and a Parseval-type identity is shown.
Dynamical Systems Computational Engineering, Finance, and Science
1 code implementation • NeurIPS 2020 • Tamara G. Grossmann, Yury Korolev, Guy Gilboa, Carola-Bibiane Schönlieb
To the best of our knowledge, this is the first approach towards learning a non-linear spectral decomposition of images.
no code implementations • 11 Jan 2020 • Alona Baruhov, Guy Gilboa
Low quality depth poses a considerable challenge to computer vision algorithms.
2 code implementations • 28 Nov 2019 • Damian Kaliroff, Guy Gilboa
We propose a new and completely data-driven approach for generating a photo-consistent image transform.
no code implementations • 12 Sep 2019 • Ester Hait-Fraenkel, Guy Gilboa
These modes are textures with small eigenvalues.
no code implementations • 4 Aug 2019 • Adam Wolff, Shachar Praisler, Ilya Tcenov, Guy Gilboa
Our model and experiments predict that, in the optimal case, about 20-60 piece-wise linear structures can approximate well a depth map.
no code implementations • 23 Mar 2017 • Martin Benning, Michael Möller, Raz Z. Nossek, Martin Burger, Daniel Cremers, Guy Gilboa, Carola-Bibiane Schönlieb
In this paper we demonstrate that the framework of nonlinear spectral decompositions based on total variation (TV) regularization is very well suited for image fusion as well as more general image manipulation tasks.
no code implementations • 27 Sep 2016 • Raz Z. Nossek, Guy Gilboa
We introduce two flows: a forward flow and an inverse flow; for which the steady state solution is a nonlinear eigenfunction.
no code implementations • 27 Sep 2016 • Ester Hait, Guy Gilboa
We propose to combine semantic data and registration algorithms to solve various image processing problems such as denoising, super-resolution and color-correction.
no code implementations • ICCV 2015 • Michael Moeller, Julia Diebold, Guy Gilboa, Daniel Cremers
This paper presents the idea of learning optimal filters for color image reconstruction based on a novel concept of nonlinear spectral image decompositions recently proposed by Guy Gilboa.
no code implementations • 15 Nov 2015 • Guy Gilboa
It is shown that in the one homogeneous case the Bregman distance can be expressed in terms of this newly defined angle.
no code implementations • 15 Nov 2015 • Dikla Horesh, Guy Gilboa
A desired texture, within a scale range, is found by fitting a surface to the local maximal responses in the spectral domain.
no code implementations • 5 Oct 2015 • Guy Gilboa, Michael Moeller, Martin Burger
We present in this paper the motivation and theory of nonlinear spectral representations, based on convex regularizing functionals.