Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Ziko, Imtiaz"'
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 simple non-linear embedding adaptation layer, which is fine-tuned on top of fixed pre-trained features for one-shot tasks, improving significantly transductive entropy-based inference for low-shot regimes. Our norm-induced transformati
Externí odkaz:
http://arxiv.org/abs/2304.06832
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
Autor:
Boudiaf, Malik, Masud, Ziko Imtiaz, Rony, Jérôme, Dolz, Jose, Ayed, Ismail Ben, Piantanida, Pablo
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision loss based
Externí odkaz:
http://arxiv.org/abs/2106.12252
We investigate a general formulation for clustering and transductive few-shot learning, which integrates prototype-based objectives, Laplacian regularization and supervision constraints from a few labeled data points. We propose a concave-convex rela
Externí odkaz:
http://arxiv.org/abs/2106.09516
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
Autor:
Boudiaf, Malik, Masud, Ziko Imtiaz, Rony, Jérôme, Dolz, José, Piantanida, Pablo, Ayed, Ismail Ben
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions for a given few-shot task, in conjunction with a supervision loss based
Externí odkaz:
http://arxiv.org/abs/2008.11297
We propose a transductive Laplacian-regularized inference for few-shot tasks. Given any feature embedding learned from the base classes, we minimize a quadratic binary-assignment function containing two terms: (1) a unary term assigning query samples
Externí odkaz:
http://arxiv.org/abs/2006.15486
Autor:
Boudiaf, Malik, Rony, Jérôme, Ziko, Imtiaz Masud, Granger, Eric, Pedersoli, Marco, Piantanida, Pablo, Ayed, Ismail Ben
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:
http://arxiv.org/abs/2003.08983
We propose a general variational framework of fair clustering, which integrates an original Kullback-Leibler (KL) fairness term with a large class of clustering objectives, including prototype or graph based. Fundamentally different from the existing
Externí odkaz:
http://arxiv.org/abs/1906.08207