| Deep inside: Autoencoders N Hubens Towards Data Science, https://medium.com/p/7e41f319999f, 2019 | 33* | 2019 |
| An experimental study of the impact of pre-training on the pruning of a convolutional neural network N Hubens, M Mancas, M Decombas, M Preda, T Zaharia, B Gosselin, ... Proceedings of the 3rd International Conference on Applications of …, 2020 | 10 | 2020 |
| One-Cycle Pruning: Pruning Convnets With Tight Training Budget N Hubens, M Mancas, B Gosselin, M Preda, T Zaharia 2022 IEEE International Conference on Image Processing (ICIP), 4128-4132, 2022 | 9 | 2022 |
| Towards Lightweight Neural Animation: Exploration of Neural Network Pruning in Mixture of Experts-based Animation Models A Maiorca, N Hubens, S Laraba, T Dutoit arXiv preprint arXiv:2201.04042, 2022 | 4 | 2022 |
| FasterAI: a library to make smaller and faster neural networks N Hubens GitHub, https://github.com/nathanhubens/fasterai, 2020 | 4* | 2020 |
| Build a simple Image Retrieval System with an Autoencoder N Hubens Medium, 2018 | 3 | 2018 |
| Improve convolutional neural network pruning by maximizing filter variety N Hubens, M Mancas, B Gosselin, M Preda, T Zaharia International Conference on Image Analysis and Processing, 379-390, 2022 | 1 | 2022 |
| Where is my mind (Looking at)? A study of the EEG–visual attention relationship V Delvigne, N Tits, L La Fisca, N Hubens, A Maiorca, H Wannous, T Dutoit, ... Informatics 9 (1), 26, 2022 | 1 | 2022 |
| Fake-buster: A lightweight solution for deepfake detection N Hubens, M Mancas, B Gosselin, M Preda, T Zaharia Applications of Digital Image Processing XLIV 11842, 146-154, 2021 | 1 | 2021 |
| Modulated self-attention convolutional network for VQA JB Delbrouck, A Maiorca, N Hubens, S Dupont arXiv preprint arXiv:1910.03343, 2019 | 1 | 2019 |
| A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation O Seddati, N Hubens, S Dupont, T Dutoit arXiv preprint arXiv:2305.18988, 2023 | | 2023 |
| Induced Feature Selection by Structured Pruning N Hubens, V Delvigne, M Mancas, B Gosselin, M Preda, T Zaharia arXiv preprint arXiv:2303.10999, 2023 | | 2023 |
| Towards lighter and faster deep neural networks with parameter pruning N Hubens Institut Polytechnique de Paris; Université de Mons, 2022 | | 2022 |
| FasterAI: A Lightweight Library for Neural Networks Compression N Hubens, M Mancas, B Gosselin, M Preda, T Zaharia Electronics 11 (22), 3789, 2022 | | 2022 |
| FasterAI: A Lightweight Library for Creating Sparse Neural Networks N Hubens arXiv preprint arXiv:2207.01088, 2022 | | 2022 |
| Towards lighter and faster deep neural networks with parameter pruning.(Compression et accélération de réseaux de neurones profonds par élagage synaptique). N Hubens University of Mons, Belgium, 2022 | | 2022 |
| Winning the Lottery with fastai N Hubens https://nathanhubens.github.io/posts/deep%20learning/2022/02/16/Lottery.html, 2022 | | 2022 |
| Which Pruning Schedule Should I Use ? N Hubens https://nathanhubens.github.io/posts/deep%20learning/2021/06/15/OneCycle.html, 2021 | | 2021 |
| FasterAI: a library to make smaller and faster neural networks N Hubens Github, https://github.com/nathanhubens/fasterai, 2020 | | 2020 |
| FasterAI N Hubens https://nathanhubens.github.io/posts/deep%20learning/2020/08/17/FasterAI.html, 2020 | | 2020 |
Matei MancasNumediart Institute for Creative Technologies, University of Mons (UMONS)Geverifieerd e-mailadres voor umons.ac.be
