1 code implementation • Neurocomputing 2023 • Atif Anwer, Samia Ainouz, Naufal M. Saad, Syed Saad Azhar Ali, Fabrice Meriaudeau
Once trained, SHMGAN is able to generate specular-free images from a single RGB image as input; without requiring any additional external labels.
1 code implementation • MDPI Sensing and Imaging 2022 • Atif Anwer, Samia Ainouz, Mohamad Naufal Mohamad Saad, Syed Saad Azhar Ali, Fabrice Meriaudeau
Specular highlights detection and removal in images is a fundamental yet non-trivial problem of interest.
no code implementations • 15 Jun 2022 • Cyprien Ruffino, Rachel Blin, Samia Ainouz, Gilles Gasso, Romain Hérault, Fabrice Meriaudeau, Stéphane Canu
Polarimetric imaging, along with deep learning, has shown improved performances on different tasks including scene analysis.
no code implementations • 24 Dec 2021 • Fabian Dubourvieux, Romaric Audigier, Angélique Loesch, Samia Ainouz, Stéphane Canu
(ii) General good practices for Pseudo-Labeling, directly deduced from the interpretation of the proposed theoretical framework, in order to improve the target re-ID performance.
no code implementations • 15 Oct 2021 • Fabian Dubourvieux, Angélique Loesch, Romaric Audigier, Samia Ainouz, Stéphane Canu
However, the effectiveness of these approaches heavily depends on the choice of some hyperparameters (HP) that affect the generation of pseudo-labels by clustering.
no code implementations • 20 Sep 2020 • Fabian Dubourvieux, Romaric Audigier, Angelique Loesch, Samia Ainouz, Stephane Canu
A challenge for re-ID is the performance preservation when a model is used on data of interest (target data) which belong to a different domain from the training data domain (source data).
no code implementations • MIDL 2019 • Jing Zhang, Caroline Petitjean, Pierre Lopez, Samia Ainouz
In this paper, we depart from this idea and propose to leverage the ability of convolutional neural networks (CNN) to directly measure the head circumference, without having to resort to handcrafted features or manually labeled segmented images.
no code implementations • 2 Oct 2019 • Rachel Blin, Samia Ainouz, Stéphane Canu, Fabrice Meriaudeau
The efficiency of the proposed method is mostly due to the high power of the polarimetry to discriminate any object by its reflective properties and on the use of deep neural networks for object detection.