Parametric Information Maximization for Generalized Category Discovery

Autor: Chiaroni, Florent, Dolz, Jose, Masud, Ziko Imtiaz, Mitiche, Amar, Ayed, Ismail Ben

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

Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?

Autor: Boudiaf, Malik, Kervadec, Hoel, Masud, Ziko Imtiaz, Piantanida, Pablo, Ayed, Ismail Ben, Dolz, Jose

We show that the way inference is performed in few-shot segmentation tasks has a substantial effect on performances -- an aspect often overlooked in the literature in favor of the meta-learning paradigm. We introduce a transductive inference for a gi

Externí odkaz: http://arxiv.org/abs/2012.06166

A Unifying Mutual Information View of Metric Learning: Cross-Entropy vs. Pairwise Losses

Autor: Boudiaf, Malik, Rony, Jérôme, Masud Ziko, Imtiaz, Ayed, Ismail, Granger, Eric, Pedersoli, Marco, Piantanida, Pablo, Ayed, Ismail Ben

Publikováno v: Computer Vision – ECCV 2020 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings
16th European Conference on Computer Vision (ECCV)
16th European Conference on Computer Vision (ECCV), Sep 2021, Glasgow (virtual), United Kingdom. pp.548-564, ⟨10.1007/978-3-030-58539-6_33⟩
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Computer Vision – ECCV 2020
Computer Vision – ECCV 2020 ISBN: 9783030585389
ECCV (6)
Computer Vision – ECCV 2020-16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VI

Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, such as sample mining or pair weighting. The standard cross-entropy los

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b738f800facd1a4b1be7a52114f7ddf8
https://hal-centralesupelec.archives-ouvertes.fr/hal-03351131