1 code implementation • 6 Feb 2024 • Idan Achituve, Idit Diamant, Arnon Netzer, Gal Chechik, Ethan Fetaya
Running a dedicated model for each task is computationally expensive and therefore there is a great interest in multi-task learning (MTL).
Ranked #1 on Multi-Task Learning on ChestX-ray14
no code implementations • 3 Jan 2024 • Idit Diamant, Amir Rosenfeld, Idan Achituve, Jacob Goldberger, Arnon Netzer
In this paper, we introduce a novel noise-learning approach tailored to address noise distribution in domain adaptation settings and learn to de-confuse the pseudo-labels.
2 code implementations • 20 Sep 2023 • Ofir Gordon, Hai Victor Habi, Arnon Netzer
Quantization of deep neural networks (DNN) has become a key element in the efforts of embedding such networks on end-user devices.
1 code implementation • 7 Dec 2022 • Idit Diamant, Roy H. Jennings, Oranit Dror, Hai Victor Habi, Arnon Netzer
We propose to reconcile this conflict by aligning the entropy minimization objective with that of the pseudo labels' cross entropy.
1 code implementation • 19 Sep 2021 • Hai Victor Habi, Reuven Peretz, Elad Cohen, Lior Dikstein, Oranit Dror, Idit Diamant, Roy H. Jennings, Arnon Netzer
Neural network quantization enables the deployment of models on edge devices.
Ranked #1 on Quantization on MS COCO
1 code implementation • 12 Apr 2021 • Idit Diamant, Oranit Dror, Hai Victor Habi, Arnon Netzer
Experimental results on the CMU-Panoptic dataset demonstrate the effectiveness of the suggested framework in generating photo-realistic images of persons with new poses that are more consistent across all views in comparison to a standard Image-to-Image baseline.
2 code implementations • ECCV 2020 • Hai Victor Habi, Roy H. Jennings, Arnon Netzer
In this work, we introduce the Hardware Friendly Mixed Precision Quantization Block (HMQ) in order to meet this requirement.
Ranked #13 on Quantization on ImageNet
no code implementations • 4 Feb 2014 • Tal Grinshpoun, Alon Grubshtein, Roie Zivan, Arnon Netzer, Amnon Meisels
Innovative algorithms that apply to the special properties of the proposed ADCOP model are presented in detail.