289 citations · 337 across the 13 of their papers we have counts for
9 papers · 1 filter
Granite Vision: a lightweight, open-source multimodal model for enterprise Intelligence
Granite Vision Team, Leonid Karlinsky, Assaf Arbelle +60
We introduce Granite Vision, a lightweight large language model with vision capabilities, specifically designed to excel in enterprise use cases, particularly in visual document un…
CHARTER: heatmap-based multi-type chart data extraction
Joseph Shtok, Sivan Harary, Ophir Azulai +3
The digital conversion of information stored in documents is a great source of knowledge. In contrast to the documents text, the conversion of the embedded documents graphics, such…
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…
StarNet: towards Weakly Supervised Few-Shot Object Detection
Leonid Karlinsky, Joseph Shtok, Amit Alfassy +8
Few-shot detection and classification have advanced significantly in recent years. Yet, detection approaches require strong annotation (bounding boxes) both for pre-training and fo…
LaSO: Label-Set Operations networks for multi-label few-shot learning
Amit Alfassy, Leonid Karlinsky, Amit Aides +5
Example synthesis is one of the leading methods to tackle the problem of few-shot learning, where only a small number of samples per class are available. However, current synthesis…
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…
Spatially-Adaptive Reconstruction in Computed Tomography using Neural Networks
Joseph Shtok, Michael Zibulevsky, Michael Elad
We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in compute…
Spatially-Adaptive Reconstruction in Computed Tomography Based on Statistical Learning
Joseph Shtok, Michael Zibulevsky, Michael Elad
We propose a direct reconstruction algorithm for Computed Tomography, based on a local fusion of a few preliminary image estimates by means of a non-linear fusion rule. One such ru…