Search Results for author:
Found 28 papers, 7 papers with code
Fast and Simple Explainability for Point Cloud Networks
We propose a fast and simple explainable AI (XAI) method for point cloud data.
DXAI: Explaining Classification by Image Decomposition
We propose a new way to explain and to visualize neural network classification through a decomposition-based explainable AI (DXAI).
Enhancing Neural Training via a Correlated Dynamics Model
Our modeling can improve training efficiency and lower communication overhead, as shown by our preliminary experiments in the context of federated learning.
Robustifying Point Cloud Networks by Refocusing
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
Additive Class Distinction Maps using Branched-GANs
We present a new model, training procedure and architecture to create precise maps of distinction between two classes of images.
EPiC: Ensemble of Partial Point Clouds for Robust Classification
In this work we propose a general ensemble framework, based on partial point cloud sampling.
Ranked #4 on
Point Cloud Classification
on PointCloud-C
Graph Laplacian for Semi-Supervised Learning
For semi-supervised problems, the common approach is to solve a constrained optimization problem, regularized by a Dirichlet energy, based on the graph-Laplacian.
The Underlying Correlated Dynamics in Neural Training
We propose in this work a model based on the correlation of the parameters' dynamics, which dramatically reduces the dimensionality.
BASiS: Batch Aligned Spectral Embedding Space
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.
Analysis of Branch Specialization and its Application in Image Decomposition
In this work, we present a methodological analysis of Branch Specialization.
How to Guide Adaptive Depth Sampling?
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.
Generalized Inversion of Nonlinear Operators
Most notable is the Moore-Penrose inverse, widely used in physics, statistics, and various fields of engineering.
Experts with Lower-Bounded Loss Feedback: A Unifying Framework
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.
Iterative Methods for Computing Eigenvectors of Nonlinear Operators
In this chapter we are examining several iterative methods for solving nonlinear eigenvalue problems.
Adaptive LiDAR Sampling and Depth Completion using Ensemble Variance
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.
Modes of Homogeneous Gradient Flows
Definitions for spectrum and filtering are given, and a Parseval-type identity is shown.
Dynamical Systems Computational Engineering, Finance, and Science
Deeply Learned Spectral Total Variation Decomposition
To the best of our knowledge, this is the first approach towards learning a non-linear spectral decomposition of images.
Unsupervised Enhancement of Real-World Depth Images Using Tri-Cycle GAN
Low quality depth poses a considerable challenge to computer vision algorithms.
PhIT-Net: Photo-consistent Image Transform for Robust Illumination Invariant Matching
We propose a new and completely data-driven approach for generating a photo-consistent image transform.
Revealing Stable and Unstable Modes of Generic Denoisers through Nonlinear Eigenvalue Analysis
These modes are textures with small eigenvalues.
Image-Guided Depth Sampling and Reconstruction
Our model and experiments predict that, in the optimal case, about 20-60 piece-wise linear structures can approximate well a depth map.
Nonlinear Spectral Image Fusion
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.
Blind Facial Image Quality Enhancement using Non-Rigid Semantic Patches
We propose to combine semantic data and registration algorithms to solve various image processing problems such as denoising, super-resolution and color-correction.
Flows Generating Nonlinear Eigenfunctions
We introduce two flows: a forward flow and an inverse flow; for which the steady state solution is a nonlinear eigenfunction.
Learning Nonlinear Spectral Filters for Color Image Reconstruction
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.
Semi-Inner-Products for Convex Functionals and Their Use in Image Decomposition
It is shown that in the one homogeneous case the Bregman distance can be expressed in terms of this newly defined angle.
Separation Surfaces in the Spectral TV Domain for Texture Decomposition
A desired texture, within a scale range, is found by fitting a surface to the local maximal responses in the spectral domain.
Nonlinear Spectral Analysis via One-homogeneous Functionals - Overview and Future Prospects
We present in this paper the motivation and theory of nonlinear spectral representations, based on convex regularizing functionals.
