no code implementations • 22 Nov 2022 • Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli
Visual counterfactual explanations identify modifications to an image that would change the prediction of a classifier.
no code implementations • 20 Apr 2021 • Claire Theobald, Bastien Arcelin, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli
We show that while a convolutional network can be trained to correctly estimate well calibrated aleatoric uncertainty, -- the uncertainty due to the presence of noise in the images -- it is unable to generate a trustworthy ellipticity distribution when exposed to previously unseen data (i. e. here, blended scenes).
no code implementations • 3 Feb 2021 • Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli
Bayesian Neural Networks (BNN) have recently emerged in the Deep Learning world for dealing with uncertainty estimation in classification tasks, and are used in many application domains such as astrophysics, autonomous driving... BNN assume a prior over the weights of a neural network instead of point estimates, enabling in this way the estimation of both aleatoric and epistemic uncertainty of the model prediction. Moreover, a particular type of BNN, namely MC Dropout, assumes a Bernoulli distribution on the weights by using Dropout. Several attempts to optimize the dropout rate exist, e. g. using a variational approach. In this paper, we present a new method called "Dropout Regulation" (DR), which consists of automatically adjusting the dropout rate during training using a controller as used in automation. DR allows for a precise estimation of the uncertainty which is comparable to the state-of-the-art while remaining simple to implement.