14 citations · 14 across the 9 of their papers we have counts for
9 papers
A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation
Omar Seddati, Nathan Hubens, Stéphane Dupont +1
Sketch-Based Image Retrieval (SBIR) is a crucial task in multimedia retrieval, where the goal is to retrieve a set of images that match a given sketch query. Researchers have alrea…
Induced Feature Selection by Structured Pruning
Nathan Hubens, Victor Delvigne, Matei Mancas +3
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, abl…
FasterAI: A Lightweight Library for Creating Sparse Neural Networks
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…
Improve Convolutional Neural Network Pruning by Maximizing Filter Variety
Nathan Hubens, Matei Mancas, Bernard Gosselin +2
Neural network pruning is a widely used strategy for reducing model storage and computing requirements. It allows to lower the complexity of the network by introducing sparsity in…
Towards Lightweight Neural Animation : Exploration of Neural Network Pruning in Mixture of Experts-based Animation Models
Antoine Maiorca, Nathan Hubens, Sohaib Laraba +1
In the past few years, neural character animation has emerged and offered an automatic method for animating virtual characters. Their motion is synthesized by a neural network. Con…
Where Is My Mind (looking at)? Predicting Visual Attention from Brain Activity
Victor Delvigne, Noé Tits, Luca La Fisca +5
Visual attention estimation is an active field of research at the crossroads of different disciplines: computer vision, artificial intelligence and medicine. One of the most common…
An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network
Nathan Hubens, Matei Mancas, Bernard Gosselin +2
In recent years, deep neural networks have known a wide success in various application domains. However, they require important computational and memory resources, which severely h…
One-Cycle Pruning: Pruning ConvNets Under a Tight Training Budget
Nathan Hubens, Matei Mancas, Bernard Gosselin +2
Introducing sparsity in a neural network has been an efficient way to reduce its complexity while keeping its performance almost intact. Most of the time, sparsity is introduced us…
Modulated Self-attention Convolutional Network for VQA
Jean-Benoit Delbrouck, Antoine Maiorca, Nathan Hubens +1
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…