Search Results for author:
Found 31 papers, 18 papers with code
Functional Brain-to-Brain Transformation with No Shared Data
Combining Functional MRI (fMRI) data across different subjects and datasets is crucial for many neuroscience tasks.
The Hidden Language of Diffusion Models
In this work, we present Conceptor, a novel method to interpret the internal representation of a textual concept by a diffusion model.
Reconstructing Training Data from Multiclass Neural Networks
Reconstructing samples from the training set of trained neural networks is a major privacy concern.
Teaching CLIP to Count to Ten
Our counting loss is deployed over automatically-created counterfactual examples, each consisting of an image and a caption containing an incorrect object count.
SinFusion: Training Diffusion Models on a Single Image or Video
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.
Imagic: Text-Based Real Image Editing with Diffusion Models
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.
Combining Internal and External Constraints for Unrolling Shutter in Videos
This allows to constrain the GS output video using video-specific constraints imposed by the RS input video.
Reconstructing Training Data from Trained Neural Networks
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
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
GANs are able to perform generation and manipulation tasks, trained on a single video.
Self-Distilled StyleGAN: Towards Generation from Internet Photos
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.
Pure Noise to the Rescue of Insufficient Data: Improving Imbalanced Classification by Training on Random Noise Images
In this paper, we present a surprisingly simple yet highly effective method to mitigate this limitation: using pure noise images as additional training data.
Ranked #1 on
Long-tail Learning
on CelebA-5
Diverse Generation from a Single Video Made Possible
GANs are able to perform generation and manipulation tasks, trained on a single video.
More Than Meets the Eye: Self-Supervised Depth Reconstruction From Brain Activity
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").
Explaining in Style: Training a GAN to explain a classifier in StyleSpace
A natural source for such attributes is the StyleSpace of StyleGAN, which is known to generate semantically meaningful dimensions in the image.
Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models
Recently, however, Single Image GANs were introduced both as a superior solution for such manipulation tasks, but also for remarkable novel generative tasks.
From Discrete to Continuous Convolution Layers
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
We demonstrate how those learned features can boost the performance of self-supervised action recognition, and can be used for video retrieval.
Across Scales & Across Dimensions: Temporal Super-Resolution using Deep Internal Learning
In particular, the higher spatial resolution of video frames provides strong examples as to how to increase the temporal resolution of that video.
Semantic Pyramid for Image Generation
We demonstrate that our model results in a versatile and flexible framework that can be used in various classic and novel image generation tasks.
Blind Super-Resolution Kernel Estimation using an Internal-GAN
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).
Ranked #5 on
Blind Super-Resolution
on DIV2KRK - 2x upscaling
From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI
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.
Natural and Adversarial Error Detection using Invariance to Image Transformations
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
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.
InGAN: Capturing and Remapping the "DNA" of a Natural Image
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.
âZero-Shotâ Super-Resolution Using Deep Internal Learning
On such images, our method outperforms SotA CNN-based SR methods, as well as previous unsupervised SR methods.
"Zero-Shot" Super-Resolution using Deep Internal Learning
On such images, our method outperforms SotA CNN-based SR methods, as well as previous unsupervised SR methods.
Ranked #46 on
Image Super-Resolution
on BSD100 - 4x upscaling
Non-Uniform Blind Deblurring by Reblurring
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.
Temporal-Needle: A view and appearance invariant video descriptor
However, to find similar actions across videos, we consider only a small subset of the descriptors - the statistical significant descriptors.
Needle-Match: Reliable Patch Matching Under High Uncertainty
Reliable patch-matching forms the basis for many algorithms (super-resolution, denoising, inpainting, etc.)
Separating Signal from Noise Using Patch Recurrence across Scales
While clean patches are obscured by severe noise in the original scale of a noisy image, noise levels drop dramatically at coarser image scales.
