Research

I’m a PhD Student based in Belgium. I am mostly interested in making neural networks smaller and faster ✂️

Hubens N. et al., “One-Cycle Pruning: Pruning ConvNets Under a Tight Training Budget”. In International Conference on Image Processing (ICIP), 2022.
Hubens N. et al., “FasterAI: A Lightweight Library for Creating Sparse Neural Networks”.In Sparsity in Neural Networks: Advancing Understanding and Practice (SNN), 2022.
Hubens N. et al., “Improve Convolutional Neural Network Pruning by Maximizing Filter Variety”. In Proceedings 21st International Conference on Image Analysis and Processing (ICIAP),2022.
Delvigne V., Tits N.,La Fisca L. , Hubens N. , Maiorca A., Wannous H. , Dutoit T. , Vandeborre J.-P. “Where Is My Mind (looking at)? Predicting Visual Attention from Brain Activity”. In MDPI Informatics, 2022
Maiorca A., Hubens N., Laraba S., Dutoit T., “Towards Lightweight Neural Animation : Exploration of Neural Network Pruning in Mixture of Experts-based Animation Models”. In Proceedings of the 17th International Conference on Computer Graphics Theory and Applications (GRAPP), 2022.

Hubens N. et al., “Fake-Buster: A Lightweight Solution for Deepfake Detection”. In Proceedings of SPIE Optical Engineering + Applications (SPIE), 2021.
Hubens N. et al., “One-Cycle Pruning: Pruning ConvNets Under a Tight Training Budget”. In Sparsity in Neural Networks: Advancing Understanding and Practice (SNN), 2021.

Hubens N. et al., “An Experimental Study of the Impact of Pre-Training on the Pruning of a Con- volutional Neural Network”. In Proceedings of the 3rd International Conference on Applications of Intelligent Systems (APPIS), 2020.

Delbroucq J.B., Hubens N., Maiorca A., Dupont S., “Modulated Self-attention Convolutional Net- work for VQA”. In NeurIPS Workshop on Visually-Grounded Interaction and Language (ViGIL), 2019.