no code implementations • 17 Dec 2023 • Maksim Makarenko, Qizhou Wang, Arturo Burguete-Lopez, Silvio Giancola, Bernard Ghanem, Luca Passone, Andrea Fratalocchi
The technology platform combines artificial intelligence hardware, processing information optically, with state-of-the-art machine vision networks, resulting in a data processing speed of 1. 2 Tb/s with hundreds of frequency bands and megapixel spatial resolution at video rates.
no code implementations • 31 Oct 2022 • Maksim Makarenko, Elnur Gasanov, Rustem Islamov, Abdurakhmon Sadiev, Peter Richtarik
We propose Adaptive Compressed Gradient Descent (AdaCGD) - a novel optimization algorithm for communication-efficient training of supervised machine learning models with adaptive compression level.
1 code implementation • CVPR 2022 • Maksim Makarenko, Arturo Burguete-Lopez, Qizhou Wang, Fedor Getman, Silvio Giancola, Bernard Ghanem, Andrea Fratalocchi
Hyperspectral imaging has attracted significant attention to identify spectral signatures for image classification and automated pattern recognition in computer vision.
no code implementations • 6 Oct 2021 • Qizhou Wang, Maksim Makarenko
This work introduced a novel GAN architecture for unsupervised image translation on the task of face style transform.
1 code implementation • 5 May 2020 • Fedor Getman, Maksim Makarenko, Arturo Burguete-Lopez, Andrea Fratalocchi
In this work, we developed an inverse design approach that allows the realization of highly efficient (up to $99\%$) ultra-flat (down to $50$nm thick) optics for vectorial light control and broadband input-output responses on a desired wavefront shape.
Optics