1 code implementation • 18 Apr 2023 • Valentin Delchevalerie, Alexandre Mayer, Adrien Bibal, Benoît Frénay
For many years, it has been shown how much exploiting equivariances can be beneficial when solving image analysis tasks.
no code implementations • 10 Feb 2023 • Arnaud Bougaham, Valentin Delchevalerie, Mohammed El Adoui, Benoît Frénay
The model would be able to identify its weaknesses by better learning how to transform an abnormal (respectively normal) image into a normal (respectively abnormal) one, helping the entire model to learn better than a single normal to normal reconstruction.
no code implementations • 25 Nov 2022 • Arnaud Bougaham, Mohammed El Adoui, Isabelle Linden, Benoît Frénay
Nevertheless, several challenges have to be faced, including imbalanced datasets, the image complexity, and the zero-false-negative (ZFN) constraint to guarantee the high-quality requirement.
no code implementations • NeurIPS 2021 • Valentin Delchevalerie, Adrien Bibal, Benoît Frénay, Alexandre Mayer
For many applications in image analysis, learning models that are invariant to translations and rotations is paramount.
1 code implementation • International Joint Conference on Neural Networks (IJCNN) 2021 • Jérôme Fink, Benoît Frénay, Laurence Meurant, Anthony Cleve
While significant progress have been made in the field of Natural Language Processing (NLP), leading the commercially available products, Sign Language Recognition (SLR) is still in its infancy.
no code implementations • 19 May 2021 • Cristina Morariu, Adrien Bibal, Rene Cutura, Benoît Frénay, Michael Sedlmair
A plethora of dimensionality reduction techniques have emerged over the past decades, leaving researchers and analysts with a wide variety of choices for reducing their data, all the more so given some techniques come with additional parametrization (e. g. t-SNE, UMAP, etc.).
no code implementations • 10 Jul 2020 • Adrien Bibal, Michael Lognoul, Alexandre de Streel, Benoît Frénay
The requirements on explainability imposed by European laws and their implications for machine learning (ML) models are not always clear.
1 code implementation • 14 May 2020 • Pieter Delobelle, Paul Temple, Gilles Perrouin, Benoît Frénay, Patrick Heymans, Bettina Berendt
These new examples are then used to retrain and improve the model in the first step.