Search Results for author: Michal Irani

Found 33 papers, 18 papers with code

The Wisdom of a Crowd of Brains: A Universal Brain Encoder

no code implementations18 Jun 2024 Roman Beliy, Navve Wasserman, Amit Zalcher, Michal Irani

This voxel-centric architecture allows the functional role of each brain-voxel to naturally emerge from the voxel-image cross-attention.

Transfer Learning

Functional Brain-to-Brain Transformation with No Shared Data

no code implementations17 Apr 2024 Navve Wasserman, Roman Beliy, Roy Urbach, Michal Irani

Combining Functional MRI (fMRI) data across different subjects and datasets is crucial for many neuroscience tasks.


Using generative AI to investigate medical imagery models and datasets

no code implementations1 Jun 2023 Oran Lang, Doron Yaya-Stupp, Ilana Traynis, Heather Cole-Lewis, Chloe R. Bennett, Courtney Lyles, Charles Lau, Michal Irani, Christopher Semturs, Dale R. Webster, Greg S. Corrado, Avinatan Hassidim, Yossi Matias, Yun Liu, Naama Hammel, Boris Babenko

In this paper, we present a method for automatic visual explanations leveraging team-based expertise by generating hypotheses of what visual signals in the images are correlated with the task.

The Hidden Language of Diffusion Models

1 code implementation1 Jun 2023 Hila Chefer, Oran Lang, Mor Geva, Volodymyr Polosukhin, Assaf Shocher, Michal Irani, Inbar Mosseri, Lior Wolf

In this work, we present Conceptor, a novel method to interpret the internal representation of a textual concept by a diffusion model.

Bias Detection Image Manipulation

Reconstructing Training Data from Multiclass Neural Networks

no code implementations5 May 2023 Gon Buzaglo, Niv Haim, Gilad Yehudai, Gal Vardi, Michal Irani

Reconstructing samples from the training set of trained neural networks is a major privacy concern.

Binary Classification

Teaching CLIP to Count to Ten

1 code implementation ICCV 2023 Roni Paiss, Ariel Ephrat, Omer Tov, Shiran Zada, Inbar Mosseri, Michal Irani, Tali Dekel

Our counting loss is deployed over automatically-created counterfactual examples, each consisting of an image and a caption containing an incorrect object count.

counterfactual Image Retrieval +4

SinFusion: Training Diffusion Models on a Single Image or Video

1 code implementation21 Nov 2022 Yaniv Nikankin, Niv Haim, Michal Irani

Our image/video-specific diffusion model (SinFusion) learns the appearance and dynamics of the single image or video, while utilizing the conditioning capabilities of diffusion models.

Diversity Image Manipulation +1

Imagic: Text-Based Real Image Editing with Diffusion Models

no code implementations CVPR 2023 Bahjat Kawar, Shiran Zada, Oran Lang, Omer Tov, Huiwen Chang, Tali Dekel, Inbar Mosseri, Michal Irani

In this paper we demonstrate, for the very first time, the ability to apply complex (e. g., non-rigid) text-guided semantic edits to a single real image.

Style Transfer

Combining Internal and External Constraints for Unrolling Shutter in Videos

no code implementations24 Jul 2022 Eyal Naor, Itai Antebi, Shai Bagon, Michal Irani

This allows to constrain the GS output video using video-specific constraints imposed by the RS input video.

Attribute Rolling Shutter Correction

Reconstructing Training Data from Trained Neural Networks

1 code implementation15 Jun 2022 Niv Haim, Gal Vardi, Gilad Yehudai, Ohad Shamir, Michal Irani

We propose a novel reconstruction scheme that stems from recent theoretical results about the implicit bias in training neural networks with gradient-based methods.

A Penny for Your (visual) Thoughts: Self-Supervised Reconstruction of Natural Movies from Brain Activity

no code implementations7 Jun 2022 Ganit Kupershmidt, Roman Beliy, Guy Gaziv, Michal Irani

Reconstructing natural videos from fMRI brain recordings is very challenging, for two main reasons: (i) As fMRI data acquisition is difficult, we only have a limited amount of supervised samples, which is not enough to cover the huge space of natural videos; and (ii) The temporal resolution of fMRI recordings is much lower than the frame rate of natural videos.


Diverse Video Generation from a Single Video

no code implementations11 May 2022 Niv Haim, Ben Feinstein, Niv Granot, Assaf Shocher, Shai Bagon, Tali Dekel, Michal Irani

GANs are able to perform generation and manipulation tasks, trained on a single video.

Video Generation

Self-Distilled StyleGAN: Towards Generation from Internet Photos

2 code implementations24 Feb 2022 Ron Mokady, Michal Yarom, Omer Tov, Oran Lang, Daniel Cohen-Or, Tali Dekel, Michal Irani, Inbar Mosseri

To meet these challenges, we proposed a StyleGAN-based self-distillation approach, which consists of two main components: (i) A generative-based self-filtering of the dataset to eliminate outlier images, in order to generate an adequate training set, and (ii) Perceptual clustering of the generated images to detect the inherent data modalities, which are then employed to improve StyleGAN's "truncation trick" in the image synthesis process.

Image Generation

Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images

1 code implementation16 Dec 2021 Shiran Zada, Itay Benou, Michal Irani

In this paper, we present a surprisingly simple yet highly effective method to mitigate this limitation: using pure noise images as additional training data.

Data Augmentation Image Classification +2

More Than Meets the Eye: Self-Supervised Depth Reconstruction From Brain Activity

1 code implementation9 Jun 2021 Guy Gaziv, Michal Irani

This is applied to both: (i) the small number of images presented to subjects in an fMRI scanner (images for which we have fMRI recordings - referred to as "paired" data), and (ii) a very large number of natural images with no fMRI recordings ("unpaired data").

Brain Decoding

Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models

2 code implementations CVPR 2022 Niv Granot, Ben Feinstein, Assaf Shocher, Shai Bagon, Michal Irani

Recently, however, Single Image GANs were introduced both as a superior solution for such manipulation tasks, but also for remarkable novel generative tasks.

Image Generation Image Manipulation

From Discrete to Continuous Convolution Layers

1 code implementation19 Jun 2020 Assaf Shocher, Ben Feinstein, Niv Haim, Michal Irani

We propose a generalization of the common Conv-layer, from a discrete layer to a Continuous Convolution (CC) Layer.

SpeedNet: Learning the Speediness in Videos

1 code implementation CVPR 2020 Sagie Benaim, Ariel Ephrat, Oran Lang, Inbar Mosseri, William T. Freeman, Michael Rubinstein, Michal Irani, Tali Dekel

We demonstrate how those learned features can boost the performance of self-supervised action recognition, and can be used for video retrieval.

Binary Classification Retrieval +2

Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal Learning

1 code implementation ECCV 2020 Liad Pollak Zuckerman, Eyal Naor, George Pisha, Shai Bagon, Michal Irani

In particular, the higher spatial resolution of video frames provides strong examples as to how to increase the temporal resolution of that video.

Video Super-Resolution

Semantic Pyramid for Image Generation

2 code implementations CVPR 2020 Assaf Shocher, Yossi Gandelsman, Inbar Mosseri, Michal Yarom, Michal Irani, William T. Freeman, Tali Dekel

We demonstrate that our model results in a versatile and flexible framework that can be used in various classic and novel image generation tasks.

General Classification Image Generation +2

Blind Super-Resolution Kernel Estimation using an Internal-GAN

4 code implementations NeurIPS 2019 Sefi Bell-Kligler, Assaf Shocher, Michal Irani

Super resolution (SR) methods typically assume that the low-resolution (LR) image was downscaled from the unknown high-resolution (HR) image by a fixed 'ideal' downscaling kernel (e. g. Bicubic downscaling).

Blind Super-Resolution Super-Resolution

From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI

2 code implementations NeurIPS 2019 Roman Beliy, Guy Gaziv, Assaf Hoogi, Francesca Strappini, Tal Golan, Michal Irani

Unfortunately, acquiring sufficient "labeled" pairs of {Image, fMRI} (i. e., images with their corresponding fMRI responses) to span the huge space of natural images is prohibitive for many reasons.

Decoder Image Reconstruction

Natural and Adversarial Error Detection using Invariance to Image Transformations

no code implementations1 Feb 2019 Yuval Bahat, Michal Irani, Gregory Shakhnarovich

Our approach is based on the observation that correctly classified images tend to exhibit robust and consistent classifications under certain image transformations (e. g., horizontal flip, small image translation, etc.).


"Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors

1 code implementation Computer Vision Foundation 2018 Yossi Gandelsman, Assaf Shocher, Michal Irani

It was shown [Ulyanov et al] that the structure of a single DIP generator network is sufficient to capture the low-level statistics of a single image.

Image Dehazing Image Segmentation +3

InGAN: Capturing and Remapping the "DNA" of a Natural Image

1 code implementation1 Dec 2018 Assaf Shocher, Shai Bagon, Phillip Isola, Michal Irani

In this paper we propose an "Internal GAN" (InGAN) - an image-specific GAN - which trains on a single input image and learns its internal distribution of patches.

"Zero-Shot" Super-Resolution using Deep Internal Learning

7 code implementations17 Dec 2017 Assaf Shocher, Nadav Cohen, Michal Irani

On such images, our method outperforms SotA CNN-based SR methods, as well as previous unsupervised SR methods.

Image Compression Image Super-Resolution

Non-Uniform Blind Deblurring by Reblurring

no code implementations ICCV 2017 Yuval Bahat, Netalee Efrat, Michal Irani

It attempts to recover a sharp image which, on one hand - results in the blurry image under our estimated blur-field, and on the other hand - maximizes the internal recurrence of patches within and across scales of the recovered sharp image.

Blind Image Deblurring Image Deblurring

Temporal-Needle: A view and appearance invariant video descriptor

no code implementations14 Dec 2016 Michal Yarom, Michal Irani

However, to find similar actions across videos, we consider only a small subset of the descriptors - the statistical significant descriptors.

Action Detection Clustering +1

Needle-Match: Reliable Patch Matching Under High Uncertainty

no code implementations CVPR 2016 Or Lotan, Michal Irani

Reliable patch-matching forms the basis for many algorithms (super-resolution, denoising, inpainting, etc.)

Denoising Patch Matching +2

Separating Signal from Noise Using Patch Recurrence across Scales

no code implementations CVPR 2013 Maria Zontak, Inbar Mosseri, Michal Irani

While clean patches are obscured by severe noise in the original scale of a noisy image, noise levels drop dramatically at coarser image scales.

Image Denoising

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