no code implementations • 16 Apr 2024 • Dani Manjah, Davide Cacciarelli, Christophe De Vleeschouwer, Benoit Macq
We present a scalable framework designed to craft efficient lightweight models for video object detection utilizing self-training and knowledge distillation techniques.
no code implementations • 7 Feb 2024 • Karim El Khoury, Tiffanie Godelaine, Simon Delvaux, Sebastien Lugan, Benoit Macq
Emergency response missions depend on the fast relay of visual information, a task to which unmanned aerial vehicles are well adapted.
1 code implementation • 13 Apr 2022 • Antoine Aspeel, Amaury Gouverneur, Raphaël M. Jungers, Benoit Macq
We prove that in terms of expected mean square error, the stochastic program filter outperforms the online filter, which itself outperforms the offline filter.
no code implementations • 16 Jul 2021 • Gaetan Rensonnet, Louise Adam, Benoit Macq
Deep neural networks (DNN) have an impressive ability to invert very complex models, i. e. to learn the generative parameters from a model's output.
no code implementations • 23 Dec 2020 • Paul Desbordes, Diksha, Benoit Macq
The importance of radiomics features for predicting patient outcome is now well-established.
no code implementations • 18 Jun 2019 • Sebastien Lugan, Paul Desbordes, Luis Xavier Ramos Tormo, Axel Legay, Benoit Macq
Distributed learning across a coalition of organizations allows the members of the coalition to train and share a model without sharing the data used to optimize this model.