Search Results for author: Meirav Galun

Found 23 papers, 10 papers with code

Controlling the Inductive Bias of Wide Neural Networks by Modifying the Kernel's Spectrum

no code implementations26 Jul 2023 Amnon Geifman, Daniel Barzilai, Ronen Basri, Meirav Galun

We leverage the duality between wide neural networks and Neural Tangent Kernels and propose a preconditioned gradient descent method, which alters the trajectory of GD.

Inductive Bias

A Kernel Perspective of Skip Connections in Convolutional Networks

no code implementations27 Nov 2022 Daniel Barzilai, Amnon Geifman, Meirav Galun, Ronen Basri

Over-parameterized residual networks (ResNets) are amongst the most successful convolutional neural architectures for image processing.

GRelPose: Generalizable End-to-End Relative Camera Pose Regression

no code implementations27 Nov 2022 Fadi Khatib, Yuval Margalit, Meirav Galun, Ronen Basri

It subsequently relates corresponding features in the two images, and finally uses a convolutional network to recover the relative rotation and translation between the respective cameras.

regression Translation

On the Spectral Bias of Convolutional Neural Tangent and Gaussian Process Kernels

no code implementations17 Mar 2022 Amnon Geifman, Meirav Galun, David Jacobs, Ronen Basri

We study the properties of various over-parametrized convolutional neural architectures through their respective Gaussian process and neural tangent kernels.

Deep Permutation Equivariant Structure from Motion

1 code implementation ICCV 2021 Dror Moran, Hodaya Koslowsky, Yoni Kasten, Haggai Maron, Meirav Galun, Ronen Basri

Existing deep methods produce highly accurate 3D reconstructions in stereo and multiview stereo settings, i. e., when cameras are both internally and externally calibrated.

Matrix Completion

Spectral Analysis of the Neural Tangent Kernel for Deep Residual Networks

no code implementations7 Apr 2021 Yuval Belfer, Amnon Geifman, Meirav Galun, Ronen Basri

Deep residual network architectures have been shown to achieve superior accuracy over classical feed-forward networks, yet their success is still not fully understood.

Learning Algebraic Multigrid Using Graph Neural Networks

1 code implementation ICML 2020 Ilay Luz, Meirav Galun, Haggai Maron, Ronen Basri, Irad Yavneh

Efficient numerical solvers for sparse linear systems are crucial in science and engineering.

Frequency Bias in Neural Networks for Input of Non-Uniform Density

no code implementations ICML 2020 Ronen Basri, Meirav Galun, Amnon Geifman, David Jacobs, Yoni Kasten, Shira Kritchman

Recent works have partly attributed the generalization ability of over-parameterized neural networks to frequency bias -- networks trained with gradient descent on data drawn from a uniform distribution find a low frequency fit before high frequency ones.

Algebraic Characterization of Essential Matrices and Their Averaging in Multiview Settings

no code implementations ICCV 2019 Yoni Kasten, Amnon Geifman, Meirav Galun, Ronen Basri

A common approach to essential matrix averaging is to separately solve for camera orientations and subsequently for camera positions.

Test

Learning to Optimize Multigrid PDE Solvers

1 code implementation25 Feb 2019 Daniel Greenfeld, Meirav Galun, Ron Kimmel, Irad Yavneh, Ronen Basri

Constructing fast numerical solvers for partial differential equations (PDEs) is crucial for many scientific disciplines.

Resultant Based Incremental Recovery of Camera Pose from Pairwise Matches

1 code implementation27 Jan 2019 Yoni Kasten, Meirav Galun, Ronen Basri

In this paper, we introduce a novel solution to the six-point online algorithm to recover the exterior parameters associated with $I_n$.

GPSfM: Global Projective SFM Using Algebraic Constraints on Multi-View Fundamental Matrices

1 code implementation CVPR 2019 Yoni Kasten, Amnon Geifman, Meirav Galun, Ronen Basri

First, given ${n \choose 2}$ fundamental matrices computed for $n$ images, we provide a complete algebraic characterization in the form of conditions that are both necessary and sufficient to enabling the recovery of camera matrices.

On Detection of Faint Edges in Noisy Images

2 code implementations22 Jun 2017 Nati Ofir, Meirav Galun, Sharon Alpert, Achi Brandt, Boaz Nadler, Ronen Basri

A fundamental question for edge detection in noisy images is how faint can an edge be and still be detected.

Edge Detection

A New Rank Constraint on Multi-view Fundamental Matrices, and its Application to Camera Location Recovery

no code implementations CVPR 2017 Soumyadip Sengupta, Tal Amir, Meirav Galun, Tom Goldstein, David W. Jacobs, Amit Singer, Ronen Basri

We show that in general, with the selection of proper scale factors, a matrix formed by stacking fundamental matrices between pairs of images has rank 6.

A Multiscale Variable-Grouping Framework for MRF Energy Minimization

no code implementations ICCV 2015 Omer Meir, Meirav Galun, Stav Yagev, Ronen Basri, Irad Yavneh

We present a multiscale approach for minimizing the energy associated with Markov Random Fields (MRFs) with energy functions that include arbitrary pairwise potentials.

Wide baseline stereo matching with convex bounded-distortion constraints

no code implementations10 Jun 2015 Meirav Galun, Tal Amir, Tal Hassner, Ronen Basri, Yaron Lipman

This paper focuses on the challenging problem of finding correspondences once approximate epipolar constraints are given.

Stereo Matching Stereo Matching Hand

Fast Detection of Curved Edges at Low SNR

3 code implementations CVPR 2016 Nati Ofir, Meirav Galun, Boaz Nadler, Ronen Basri

Detecting edges is a fundamental problem in computer vision with many applications, some involving very noisy images.

Edge Detection

Large Scale Correlation Clustering Optimization

2 code implementations13 Dec 2011 Shai Bagon, Meirav Galun

This analogy allows us to suggest several new optimization algorithms, which exploit the intrinsic "model-selection" capability of the functional to automatically recover the underlying number of clusters.

Clustering Face Identification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.