289 citations · 776 across the 10 of their papers we have counts for
12 papers
FETA: Towards Specializing Foundation Models for Expert Task Applications
Amit Alfassy, Assaf Arbelle, Oshri Halimi +10
Foundation Models (FMs) have demonstrated unprecedented capabilities including zero-shot learning, high fidelity data synthesis, and out of domain generalization. However, as we sh…
Detector-Free Weakly Supervised Grounding by Separation
Assaf Arbelle, Sivan Doveh, Amit Alfassy +14
Nowadays, there is an abundance of data involving images and surrounding free-form text weakly corresponding to those images. Weakly Supervised phrase-Grounding (WSG) deals with th…
ISP Distillation
Eli Schwartz, Alex Bronstein, Raja Giryes
Nowadays, many of the images captured are `observed' by machines only and not by humans, e.g., in autonomous systems. High-level machine vision models, such as object recognition o…
Fine-grained Angular Contrastive Learning with Coarse Labels
Guy Bukchin, Eli Schwartz, Kate Saenko +4
Few-shot learning methods offer pre-training techniques optimized for easier later adaptation of the model to new classes (unseen during training) using one or a few examples. This…
MetAdapt: Meta-Learned Task-Adaptive Architecture for Few-Shot Classification
Sivan Doveh, Eli Schwartz, Chao Xue +4
Few-Shot Learning (FSL) is a topic of rapidly growing interest. Typically, in FSL a model is trained on a dataset consisting of many small tasks (meta-tasks) and learns to adapt to…
Baby steps towards few-shot learning with multiple semantics
Eli Schwartz, Leonid Karlinsky, Rogerio Feris +2
Learning from one or few visual examples is one of the key capabilities of humans since early infancy, but is still a significant challenge for modern AI systems. While considerabl…
Beholder-GAN: Generation and Beautification of Facial Images with Conditioning on Their Beauty Level
Nir Diamant, Dean Zadok, Chaim Baskin +2
Beauty is in the eye of the beholder. This maxim, emphasizing the subjectivity of the perception of beauty, has enjoyed a wide consensus since ancient times. In the digitalera, dat…
NICE: Noise Injection and Clamping Estimation for Neural Network Quantization
Chaim Baskin, Natan Liss, Yoav Chai +5
Convolutional Neural Networks (CNN) are very popular in many fields including computer vision, speech recognition, natural language processing, to name a few. Though deep learning…
Delta-encoder: an effective sample synthesis method for few-shot object recognition
Eli Schwartz, Leonid Karlinsky, Joseph Shtok +6
Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision. In this work, we proposes a simple yet effective met…
RepMet: Representative-based metric learning for classification and one-shot object detection
Leonid Karlinsky, Joseph Shtok, Sivan Harary +5
Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each ca…
UNIQ: Uniform Noise Injection for Non-Uniform Quantization of Neural Networks
Chaim Baskin, Eli Schwartz, Evgenii Zheltonozhskii +4
We present a novel method for neural network quantization that emulates a non-uniform -quantile quantizer, which adapts to the distribution of the quantized parameters. Our appr…
DeepISP: Towards Learning an End-to-End Image Processing Pipeline
Eli Schwartz, Raja Giryes, Alex M. Bronstein
We present DeepISP, a full end-to-end deep neural model of the camera image signal processing (ISP) pipeline. Our model learns a mapping from the raw low-light mosaiced image to th…