327 citations · 726 across the 29 of their papers we have counts for
36 papers
Progressive Photorealistic Simplification
Adi Rosenthal, Dana Berman, Yedid Hoshen +1
Existing image simplification techniques often rely on Non-Photorealistic Rendering (NPR), transforming photographs into stylized sketches, cartoons, or paintings. While effective…
Dreamix: Video Diffusion Models are General Video Editors
Eyal Molad, Eliahu Horwitz, Dani Valevski +5
Text-driven image and video diffusion models have recently achieved unprecedented generation realism. While diffusion models have been successfully applied for image editing, very…
Conffusion: Confidence Intervals for Diffusion Models
Eliahu Horwitz, Yedid Hoshen
Diffusion models have become the go-to method for many generative tasks, particularly for image-to-image generation tasks such as super-resolution and inpainting. Current diffusion…
Anomaly Detection Requires Better Representations
Tal Reiss, Niv Cohen, Eliahu Horwitz +2
Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during tr…
Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors
Niv Cohen, Jonathan Kahana, Yedid Hoshen
Anomaly detection methods strive to discover patterns that differ from the norm in a semantic way. This goal is ambiguous as a data point differing from the norm by an attribute e.…
Unsupervised Word Segmentation using K Nearest Neighbors
Tzeviya Sylvia Fuchs, Yedid Hoshen, Joseph Keshet
In this paper, we propose an unsupervised kNN-based approach for word segmentation in speech utterances. Our method relies on self-supervised pre-trained speech representations, an…
A Contrastive Objective for Learning Disentangled Representations
Jonathan Kahana, Yedid Hoshen
Learning representations of images that are invariant to sensitive or unwanted attributes is important for many tasks including bias removal and cross domain retrieval. Here, our o…
Time Series Anomaly Detection by Cumulative Radon Features
Yedid Hoshen
Detecting anomalous time series is key for scientific, medical and industrial tasks, but is challenging due to its inherent unsupervised nature. In recent years, progress has been…
Semantic Segmentation In-the-Wild Without Seeing Any Segmentation Examples
Nir Zabari, Yedid Hoshen
Semantic segmentation is a key computer vision task that has been actively researched for decades. In recent years, supervised methods have reached unprecedented accuracy, however…
Out-of-Distribution Detection Without Class Labels
Niv Cohen, Ron Abutbul, Yedid Hoshen
Out-of-distribution detection seeks to identify novelties, samples that deviate from the norm. The task has been found to be quite challenging, particularly in the case where the n…
The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design
Yoav Levine, Noam Wies, Daniel Jannai +3
Pretraining Neural Language Models (NLMs) over a large corpus involves chunking the text into training examples, which are contiguous text segments of sizes processable by the neur…
Image Shape Manipulation from a Single Augmented Training Sample
Yael Vinker, Eliahu Horwitz, Nir Zabari +1
In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single ima…
An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild
Aviv Gabbay, Niv Cohen, Yedid Hoshen
Unsupervised disentanglement has been shown to be theoretically impossible without inductive biases on the models and the data. As an alternative approach, recent methods rely on l…
Mean-Shifted Contrastive Loss for Anomaly Detection
Tal Reiss, Yedid Hoshen
Deep anomaly detection methods learn representations that separate between normal and anomalous images. Although self-supervised representation learning is commonly used, small dat…
Scaling-up Disentanglement for Image Translation
Aviv Gabbay, Yedid Hoshen
Image translation methods typically aim to manipulate a set of labeled attributes (given as supervision at training time e.g. domain label) while leaving the unlabeled attributes i…
Membership Inference Attacks are Easier on Difficult Problems
Avital Shafran, Shmuel Peleg, Yedid Hoshen
Membership inference attacks (MIA) try to detect if data samples were used to train a neural network model, e.g. to detect copyright abuses. We show that models with higher dimensi…
PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation
Tal Reiss, Niv Cohen, Liron Bergman +1
Anomaly detection methods require high-quality features. In recent years, the anomaly detection community has attempted to obtain better features using advances in deep self-superv…
Improving Style-Content Disentanglement in Image-to-Image Translation
Aviv Gabbay, Yedid Hoshen
Unsupervised image-to-image translation methods have achieved tremendous success in recent years. However, it can be easily observed that their models contain significant entanglem…
Image Shape Manipulation from a Single Augmented Training Sample
Yael Vinker, Eliahu Horwitz, Nir Zabari +1
In this paper, we present DeepSIM, a generative model for conditional image manipulation based on a single image. We find that extensive augmentation is key for enabling single ima…
Classification-Based Anomaly Detection for General Data
Liron Bergman, Yedid Hoshen
Anomaly detection, finding patterns that substantially deviate from those seen previously, is one of the fundamental problems of artificial intelligence. Recently, classification-b…
Sub-Image Anomaly Detection with Deep Pyramid Correspondences
Niv Cohen, Yedid Hoshen
Nearest neighbor (kNN) methods utilizing deep pre-trained features exhibit very strong anomaly detection performance when applied to entire images. A limitation of kNN methods is t…
Training End-to-end Single Image Generators without GANs
Yael Vinker, Nir Zabari, Yedid Hoshen
We present AugurOne, a novel approach for training single image generative models. Our approach trains an upscaling neural network using non-affine augmentations of the (single) in…
Deep Nearest Neighbor Anomaly Detection
Liron Bergman, Niv Cohen, Yedid Hoshen
Nearest neighbors is a successful and long-standing technique for anomaly detection. Significant progress has been recently achieved by self-supervised deep methods (e.g. RotNet).…
Crypto-Oriented Neural Architecture Design
Avital Shafran, Gil Segev, Shmuel Peleg +1
As neural networks revolutionize many applications, significant privacy conflicts between model users and providers emerge. The cryptography community developed a variety of techni…