Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Chiaroni, Florent"'
Autor:
Mounsaveng, Saypraseuth, Chiaroni, Florent, Boudiaf, Malik, Pedersoli, Marco, Ayed, Ismail Ben
Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest. Numerous tricks and techniques have been proposed to ensure robust learning on arbitrary streams of unlabeled data. However, assessi
Externí odkaz:
http://arxiv.org/abs/2310.02416
Autor:
Nicolas, Julien, Chiaroni, Florent, Ziko, Imtiaz, Ahmad, Ola, Desrosiers, Christian, Dolz, Jose
Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-the-art domain incremental learning (DIL) methods perform satisfactorily
Externí odkaz:
http://arxiv.org/abs/2307.05707
We introduce a Parametric Information Maximization (PIM) model for the Generalized Category Discovery (GCD) problem. Specifically, we propose a bi-level optimization formulation, which explores a parameterized family of objective functions, each eval
Externí odkaz:
http://arxiv.org/abs/2212.00334
We explore clustering the softmax predictions of deep neural networks and introduce a novel probabilistic clustering method, referred to as k-sBetas. In the general context of clustering discrete distributions, the existing methods focused on explori
Externí odkaz:
http://arxiv.org/abs/2208.00287
Nowadays, autonomous driving systems can detect, segment, and classify the surrounding obstacles using a monocular camera. However, state-of-the-art methods solving these tasks generally perform a fully supervised learning process and require a large
Externí odkaz:
http://arxiv.org/abs/1910.09094
Autor:
Chiaroni, Florent, Khodabandelou, Ghazaleh, Rahal, Mohamed-Cherif, Hueber, Nicolas, Dufaux, Frederic
With surge of available but unlabeled data, Positive Unlabeled (PU) learning is becoming a thriving challenge. This work deals with this demanding task for which recent GAN-based PU approaches have demonstrated promising results. Generative adversari
Externí odkaz:
http://arxiv.org/abs/1910.01968
Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled training data.
Externí odkaz:
http://arxiv.org/abs/1910.01636
Autor:
Chiaroni, Florent, Khodabandelou, Ghazaleh, Rahal, Mohamed-Cherif, Hueber, Nicolas, Dufaux, Frederic
Publikováno v:
In Pattern Recognition November 2020 107
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence; December 2024, Vol. 46 Issue: 12 p9123-9138, 16p
Autor:
Chiaroni, Florent
Publikováno v:
Signal and Image processing. Université Paris-Saclay, 2020. English. ⟨NNT : 2020UPASC006⟩
In the context of autonomous vehicle perception, the interest of the research community for deep learning approaches has continuously grown since the last decade. This can be explained by the fact that deep learning techniques provide nowadays state-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______212::b89d9a856d8af343d1123d1d8add8433
https://tel.archives-ouvertes.fr/tel-02881904
https://tel.archives-ouvertes.fr/tel-02881904