no code implementations • 15 Dec 2020 • Karol Desnos, Nicolas Sourbier, Pierre-Yves Raumer, Olivier Gesny, Maxime Pelcat
The impact of customizable instructions on the outcome of a training process is demonstrated on a state-of-the-art reinforcement learning environment.
no code implementations • 6 May 2020 • Shanxin Yuan, Radu Timofte, Ales Leonardis, Gregory Slabaugh, Xiaotong Luo, Jiangtao Zhang, Yanyun Qu, Ming Hong, Yuan Xie, Cuihua Li, Dejia Xu, Yihao Chu, Qingyan Sun, Shuai Liu, Ziyao Zong, Nan Nan, Chenghua Li, Sangmin Kim, Hyungjoon Nam, Jisu Kim, Jechang Jeong, Manri Cheon, Sung-Jun Yoon, Byungyeon Kang, Junwoo Lee, Bolun Zheng, Xiaohong Liu, Linhui Dai, Jun Chen, Xi Cheng, Zhen-Yong Fu, Jian Yang, Chul Lee, An Gia Vien, Hyunkook Park, Sabari Nathan, M. Parisa Beham, S Mohamed Mansoor Roomi, Florian Lemarchand, Maxime Pelcat, Erwan Nogues, Densen Puthussery, Hrishikesh P. S, Jiji C. V, Ashish Sinha, Xuan Zhao
Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image.
no code implementations • 18 Feb 2020 • Florian Lemarchand, Erwan Nogues, Maxime Pelcat
When the target noise is complex, e. g. composed of an unknown mixture of primary noises with unknown intensity, fully supervised solutions are limited by the difficulty to build a suited training set for the problem.
2 code implementations • 18 Oct 2019 • Florian Lemarchand, Eduardo Fernandes Montesuma, Maxime Pelcat, Erwan Nogues
Image denoising has recently taken a leap forward due to machine learning.
2 code implementations • 16 Oct 2019 • Florian Lemarchand, Cyril Marlin, Florent Montreuil, Erwan Nogues, Maxime Pelcat
This paper proposes an upgraded electro-magnetic side-channel attack that automatically reconstructs the intercepted data.
1 code implementation • 30 Jun 2018 • Kamel Abdelouahab, François Berry, Maxime Pelcat
Convolutional Neural Networks (CNNs) are computationally intensive algorithms that currently require dedicated hardware to be executed.
Distributed, Parallel, and Cluster Computing Hardware Architecture
no code implementations • 26 May 2018 • Kamel Abdelouahab, Maxime Pelcat, Jocelyn Serot, François Berry
This paper presents a state-of-the-art of CNN inference accelerators over FPGAs.
1 code implementation • 20 Nov 2017 • Kamel Abdelouahab, Maxime Pelcat, Jocelyn Sérot, Cédric Bourrasset, François Berry, Jocelyn Serot
Deep Convolutional Neural Networks (CNNs) are the state-of-the-art in image classification.
no code implementations • 4 May 2017 • Kamel Abdelouahab, Maxime Pelcat, Jocelyn Serot, Cedric Bourrasset, Jean-Charles Quinton, François Berry
Deep Convolutional Neural Networks (CNNs) are the state of the art systems for image classification and scene understating.
Other Computer Science
no code implementations • 21 Mar 2017 • Kamel Abdelouahab, Cedric Bourrasset, Maxime Pelcat, François Berry, Jean-Charles Quinton, Jocelyn Serot
Deep Neural Networks are becoming the de-facto standard models for image understanding, and more generally for computer vision tasks.