Raja Giryes

Publications
Influence

Robust Large Margin Deep Neural Networks

Jure Sokolic, Raja Giryes, G. Sapiro, M. Rodrigues
Computer Science, Mathematics
IEEE Transactions on Signal Processing
15 August 2017

The generalization error of deep neural networks via their classification margin is studied in this paper. Expand

Rana Hanocka, A. Hertz, N. Fish, Raja Giryes, S. Fleishman, D. Cohen-Or
Computer Science, Mathematics
ACM Trans. Graph.
2019

We utilize the unique properties of the mesh for direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes. Expand

Learned Convolutional Sparse Coding

Hillel Sreter, Raja Giryes
Computer Science, Engineering
IEEE International Conference on Acoustics…
1 November 2017

We propose a convolutional recurrent sparse auto-encoder model that learns a task-driven sparse Convolutional Dictionary and produces an approximate sparse code over the learned dictionary. Expand

Improving DNN Robustness to Adversarial Attacks using Jacobian Regularization

Daniel Jakubovitz, Raja Giryes
Computer Science, Mathematics
ECCV
23 March 2018

We apply the Frobenius norm of the Jacobian of the network, which is applied as post-processing, after regular training has finished. Expand

ASAP: Architecture Search, Anneal and Prune

Asaf Noy, Niv Nayman, +5 authors L. Zelnik-Manor
Computer Science, Mathematics
AISTATS
8 April 2019

In this paper, we propose a differentiable search space that allows the annealing of architecture weights, while gradually pruning inferior operations. Expand

Poisson Inverse Problems by the Plug-and-Play scheme

A. Rond, Raja Giryes, Michael Elad
Computer Science, Mathematics
J. Vis. Commun. Image Represent.
8 November 2015

The Anscombe transform offers an approximate conversion of a Poisson random variable into a Gaussian one, and becomes handy in various inverse problems with Poisson noise contamination. Expand

Image Restoration by Iterative Denoising and Backward Projections

Tom Tirer, Raja Giryes
Computer Science, Medicine
IEEE Transactions on Image Processing
18 October 2017

We propose an alternative method for solving linear inverse problems using off-the-shelf denoisers, which requires less parameter tuning than the P&P approach for image inpainting and deblurring. Expand

Delta-encoder: an effective sample synthesis method for few-shot object recognition

Eli Schwartz, Leonid Karlinsky, +6 authors A. Bronstein
Computer Science
NeurIPS
12 June 2018

We propose a simple yet effective method for few-shot (and one-shot) object-recognition, based on a modified auto-encoder that learns to synthesize new samples for an unseen category just by seeing few examples from it. Expand

The Projected GSURE for Automatic Parameter Tuning in Iterative Shrinkage Methods

Raja Giryes, Michael Elad, Yonina C. Eldar
Computer Science, Mathematics
ArXiv
21 March 2010

We use the projected Generalized Stein Unbiased Risk Estimator (GSURE) for determining the threshold value lambda in iterative shrinkage methods for image deblurring and image zooming. Expand

Sparsity-Based Poisson Denoising With Dictionary Learning

Raja Giryes, Michael Elad
Computer Science, Mathematics
IEEE Transactions on Image Processing
17 September 2013

The problem of Poisson denoising appears in various imaging applications, such as low-light photography, medical imaging, and microscopy. Expand

Recommended Authors