12 citations · 15 across the 8 of their papers we have counts for
8 papers
Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators
Pierre Nodet, Thomas George
We adapt two classical statistical estimators for quantifying uncertainty to modern deep learning, in order to provide clearer insights into uncertainty attributable to two sources…
Calibration improves detection of mislabeled examples
Ilies Chibane, Thomas George, Pierre Nodet +1
Mislabeled data is a pervasive issue that undermines the performance of machine learning systems in real-world applications. An effective approach to mitigate this problem is to de…
Mislabeled examples detection viewed as probing machine learning models: concepts, survey and extensive benchmark
Thomas George, Pierre Nodet, Alexis Bondu +1
Mislabeled examples are ubiquitous in real-world machine learning datasets, advocating the development of techniques for automatic detection. We show that most mislabeled detection…
Biquality Learning: a Framework to Design Algorithms Dealing with Closed-Set Distribution Shifts
Pierre Nodet, Vincent Lemaire, Alexis Bondu +1
Training machine learning models from data with weak supervision and dataset shifts is still challenging. Designing algorithms when these two situations arise has not been explored…
biquality-learn: a Python library for Biquality Learning
Pierre Nodet, Vincent Lemaire, Alexis Bondu +1
The democratization of Data Mining has been widely successful thanks in part to powerful and easy-to-use Machine Learning libraries. These libraries have been particularly tailored…
Contrastive Representations for Label Noise Require Fine-Tuning
Pierre Nodet, Vincent Lemaire, Alexis Bondu +1
In this paper we show that the combination of a Contrastive representation with a label noise-robust classification head requires fine-tuning the representation in order to achieve…
From Weakly Supervised Learning to Biquality Learning: an Introduction
Pierre Nodet, Vincent Lemaire, Alexis Bondu +2
The field of Weakly Supervised Learning (WSL) has recently seen a surge of popularity, with numerous papers addressing different types of "supervision deficiencies". In WSL use cas…
Importance Reweighting for Biquality Learning
Pierre Nodet, Vincent Lemaire, Alexis Bondu +1
The field of Weakly Supervised Learning (WSL) has recently seen a surge of popularity, with numerous papers addressing different types of "supervision deficiencies", namely: poor q…