Search Results for author: Tomer Michaeli

Found 28 papers, 10 papers with code

Unique Properties of Wide Minima in Deep Networks

no code implementations ICML 2020 Rotem Mulayoff, Tomer Michaeli

In this paper, we characterize the wide minima in linear neural networks trained with a quadratic loss.

A Theory of the Distortion-Perception Tradeoff in Wasserstein Space

no code implementations6 Jul 2021 Dror Freirich, Tomer Michaeli, Ron Meir

In this paper, we derive a closed form expression for this distortion-perception (DP) function for the mean squared-error (MSE) distortion and the Wasserstein-2 perception index.

Image Restoration

Sparsity Aware Normalization for GANs

no code implementations3 Mar 2021 Idan Kligvasser, Tomer Michaeli

Generative adversarial networks (GANs) are known to benefit from regularization or normalization of their critic (discriminator) network during training.

Image-to-Image Translation Translation

GAN "Steerability" without optimization

1 code implementation ICLR 2021 Nurit Spingarn-Eliezer, Ron Banner, Tomer Michaeli

However, all existing techniques rely on an optimization procedure to expose those directions, and offer no control over the degree of allowed interaction between different transformations.

Contrastive Divergence Learning is a Time Reversal Adversarial Game

no code implementations ICLR 2021 Omer Yair, Tomer Michaeli

In this paper, we present an alternative derivation of CD that does not require any approximation and sheds new light on the objective that is actually being optimized by the algorithm.

Learning an optimal PSF-pair for ultra-dense 3D localization microscopy

no code implementations29 Sep 2020 Elias Nehme, Boris Ferdman, Lucien E. Weiss, Tal Naor, Daniel Freedman, Tomer Michaeli, Yoav Shechtman

A long-standing challenge in multiple-particle-tracking is the accurate and precise 3D localization of individual particles at close proximity.

What's in the Image? Explorable Decoding of Compressed Images

no code implementations CVPR 2021 Yuval Bahat, Tomer Michaeli

In spite of this fact, existing decompression algorithms typically produce only a single output, and do not allow the viewer to explore the set of images that map to the given compressed code.

Image Restoration Super-Resolution

Unique Properties of Flat Minima in Deep Networks

no code implementations11 Feb 2020 Rotem Mulayoff, Tomer Michaeli

In this paper, we characterize the flat minima in linear neural networks trained with a quadratic loss.

Explorable Super Resolution

2 code implementations CVPR 2020 Yuval Bahat, Tomer Michaeli

Single image super resolution (SR) has seen major performance leaps in recent years.

Image Super-Resolution

DeepSTORM3D: dense three dimensional localization microscopy and point spread function design by deep learning

1 code implementation21 Jun 2019 Elias Nehme, Daniel Freedman, Racheli Gordon, Boris Ferdman, Lucien E. Weiss, Onit Alalouf, Reut Orange, Tomer Michaeli, Yoav Shechtman

Localization microscopy is an imaging technique in which the positions of individual nanoscale point emitters (e. g. fluorescent molecules) are determined at high precision from their images.

Super-Resolution

The effectiveness of layer-by-layer training using the information bottleneck principle

no code implementations ICLR 2019 Adar Elad, Doron Haviv, Yochai Blau, Tomer Michaeli

The recently proposed information bottleneck (IB) theory of deep nets suggests that during training, each layer attempts to maximize its mutual information (MI) with the target labels (so as to allow good prediction accuracy), while minimizing its MI with the input (leading to effective compression and thus good generalization).

Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff

no code implementations23 Jan 2019 Yochai Blau, Tomer Michaeli

Lossy compression algorithms are typically designed and analyzed through the lens of Shannon's rate-distortion theory, where the goal is to achieve the lowest possible distortion (e. g., low MSE or high SSIM) at any given bit rate.

SSIM

Dense xUnit Networks

1 code implementation27 Nov 2018 Idan Kligvasser, Tomer Michaeli

For example, on ImageNet, our DxNet outperforms a ReLU-based DenseNet having 30% more parameters and achieves state-of-the-art results for this budget of parameters.

Denoising Image Restoration +1

The 2018 PIRM Challenge on Perceptual Image Super-resolution

5 code implementations20 Sep 2018 Yochai Blau, Roey Mechrez, Radu Timofte, Tomer Michaeli, Lihi Zelnik-Manor

This paper reports on the 2018 PIRM challenge on perceptual super-resolution (SR), held in conjunction with the Perceptual Image Restoration and Manipulation (PIRM) workshop at ECCV 2018.

Image Restoration Image Super-Resolution

Revealing Common Statistical Behaviors in Heterogeneous Populations

no code implementations ICML 2018 Andrey Zhitnikov, Rotem Mulayoff, Tomer Michaeli

In many areas of neuroscience and biological data analysis, it is desired to reveal common patterns among a group of subjects.

Modifying Non-Local Variations Across Multiple Views

no code implementations CVPR 2018 Tal Tlusty, Tomer Michaeli, Tali Dekel, Lihi Zelnik-Manor

We present an algorithm for modifying small non-local variations between repeating structures and patterns in multiple images of the same scene.

Multi-Scale Weighted Nuclear Norm Image Restoration

no code implementations CVPR 2018 Noam Yair, Tomer Michaeli

A prominent property of natural images is that groups of similar patches within them tend to lie on low-dimensional subspaces.

Deblurring Image Denoising +1

Deformation Aware Image Compression

no code implementations CVPR 2018 Tamar Rott Shaham, Tomer Michaeli

Lossy compression algorithms aim to compactly encode images in a way which enables to restore them with minimal error.

Image Compression SSIM

Deep-STORM: super-resolution single-molecule microscopy by deep learning

2 code implementations29 Jan 2018 Elias Nehme, Lucien E. Weiss, Tomer Michaeli, Yoav Shechtman

We present an ultra-fast, precise, parameter-free method, which we term Deep-STORM, for obtaining super-resolution images from stochastically-blinking emitters, such as fluorescent molecules used for localization microscopy.

Optics

Joint autoencoders: a flexible meta-learning framework

no code implementations ICLR 2018 Baruch Epstein, Ron Meir, Tomer Michaeli

Ideally one would like to allow both the data for the current task and for previous related tasks to self-organize the learning system in such a way that commonalities and differences between the tasks are learned in a data-driven fashion.

Domain Adaptation Meta-Learning +1

xUnit: Learning a Spatial Activation Function for Efficient Image Restoration

1 code implementation CVPR 2018 Idan Kligvasser, Tamar Rott Shaham, Tomer Michaeli

However, state-of-the-art results are typically achieved by very deep networks, which can reach tens of layers with tens of millions of parameters.

Denoising Image Restoration +1

The Perception-Distortion Tradeoff

1 code implementation CVPR 2018 Yochai Blau, Tomer Michaeli

Image restoration algorithms are typically evaluated by some distortion measure (e. g. PSNR, SSIM, IFC, VIF) or by human opinion scores that quantify perceived perceptual quality.

Image Restoration SSIM +1

Joint auto-encoders: a flexible multi-task learning framework

no code implementations30 May 2017 Baruch Epstein. Ron Meir, Tomer Michaeli

Ideally one would like to allow both the data for the current task and for previous related tasks to self-organize the learning system in such a way that commonalities and differences between the tasks are learned in a data-driven fashion.

Domain Adaptation Multi-Task Learning

Non-Redundant Spectral Dimensionality Reduction

no code implementations11 Dec 2016 Yochai Blau, Tomer Michaeli

Our approach relies on replacing the orthogonality constraints underlying those methods by unpredictability constraints.

Dimensionality Reduction

Nonparametric Canonical Correlation Analysis

no code implementations16 Nov 2015 Tomer Michaeli, Weiran Wang, Karen Livescu

Several nonlinear extensions of the original linear CCA have been proposed, including kernel and deep neural network methods.

Representation Learning

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