no code implementations • 24 Sep 2023 • Eduardo de O. Andrade, Igor Garcia Ballhausen Sampaio, Joris Guérin, José Viterbo
We combine the use of two types of adversarial attacks, P-FGSM and Deep Mis-Ranking, applied to two popular Re-ID models: IDE (ResNet-50) and AlignedReID.
no code implementations • 29 Nov 2022 • Joris Guérin, Kevin Delmas, Raul Sena Ferreira, Jérémie Guiochet
In this work, we argue that OOD detection is not a well-suited framework to design efficient runtime monitors and that it is more relevant to evaluate monitors based on their ability to discard incorrect predictions.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 12 Feb 2021 • Igor Garcia Ballhausen Sampaio, Luigy Machaca, José Viterbo, Joris Guérin
To do this, we created a Blender script that generates realistic labeled datasets of images containing the object, which are then used for training the OD model.
no code implementations • 2 Sep 2020 • Felix O. Sumari, Luigy Machaca, Jose Huaman, Esteban W. G. Clua, Joris Guérin
With the major adoption of automation for cities security, person re-identification (Re-ID) has been extensively studied recently.
1 code implementation • 26 Jul 2018 • Joris Guérin, Olivier Gibaru, Eric Nyiri, Stéphane Thiery, Byron Boots
Although deep learning has facilitated progress in image understanding, a robot's performance in problems like object recognition often depends on the angle from which the object is observed.
1 code implementation • 20 Jul 2018 • Joris Guérin, Byron Boots
For many image clustering problems, replacing raw image data with features extracted by a pretrained convolutional neural network (CNN), leads to better clustering performance.
no code implementations • 10 Jul 2017 • Joris Guérin, Olivier Gibaru, Eric Nyiri, Stéphane Thiery
Unlike classification, position labels cannot be assigned manually by humans.
2 code implementations • 6 Jul 2017 • Joris Guérin, Olivier Gibaru, Stéphane Thiery, Eric Nyiri
This paper aims at providing insight on the transferability of deep CNN features to unsupervised problems.
no code implementations • 22 Mar 2017 • Joris Guérin, Olivier Gibaru, Stéphane Thiery, Eric Nyiri
This paper describes a method for clustering data that are spread out over large regions and which dimensions are on different scales of measurement.