no code implementations • 30 May 2023 • Omar Seddati, Nathan Hubens, Stéphane Dupont, Thierry Dutoit
Then, we introduce a Relative Triplet Loss (RTL), an adapted triplet loss to overcome those limitations through loss weighting based on anchors similarity.
no code implementations • 20 Mar 2023 • Nathan Hubens, Victor Delvigne, Matei Mancas, Bernard Gosselin, Marius Preda, Titus Zaharia
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years.
no code implementations • 3 Jul 2022 • Nathan Hubens
FasterAI is a PyTorch-based library, aiming to facilitate the utilization of deep neural networks compression techniques such as sparsification, pruning, knowledge distillation, or regularization.
no code implementations • 11 Mar 2022 • Nathan Hubens, Matei Mancas, Bernard Gosselin, Marius Preda, Titus Zaharia
This technique ensures that the criteria of selection focuses on redundant filters, while retaining the rare ones, thus maximizing the variety of remaining filters.
no code implementations • 11 Jan 2022 • Victor Delvigne, Noé Tits, Luca La Fisca, Nathan Hubens, Antoine Maiorca, Hazem Wannous, Thierry Dutoit, Jean-Philippe Vandeborre
The codes and dataset considered in this paper have been made available at \url{https://figshare. com/s/3e353bd1c621962888ad} to promote research in the field.
no code implementations • 11 Jan 2022 • Antoine Maiorca, Nathan Hubens, Sohaib Laraba, Thierry Dutoit
Their motion is synthesized by a neural network.
no code implementations • 15 Dec 2021 • Nathan Hubens, Matei Mancas, Bernard Gosselin, Marius Preda, Titus Zaharia
Neural networks usually involve a large number of parameters, which correspond to the weights of the network.
1 code implementation • 5 Jul 2021 • Nathan Hubens, Matei Mancas, Bernard Gosselin, Marius Preda, Titus Zaharia
Most of the time, sparsity is introduced using a three-stage pipeline: 1) train the model to convergence, 2) prune the model according to some criterion, 3) fine-tune the pruned model to recover performance.
no code implementations • 8 Oct 2019 • Jean-Benoit Delbrouck, Antoine Maiorca, Nathan Hubens, Stéphane Dupont
As new data-sets for real-world visual reasoning and compositional question answering are emerging, it might be needed to use the visual feature extraction as a end-to-end process during training.