Výsledky vyhledávání - "Ziko, Imtiaz Masud"

Report

Task Adaptive Feature Transformation for One-Shot Learning

Autor: Ziko, Imtiaz Masud, Lecue, Freddy, Ayed, Ismail Ben

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

Zobrazit plný text záznamu

Report

Transductive Few-Shot Learning: Clustering is All You Need?

Autor: Ziko, Imtiaz Masud, Boudiaf, Malik, Dolz, Jose, Granger, Eric, Ayed, Ismail Ben

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

Zobrazit plný text záznamu

Report

Laplacian Regularized Few-Shot Learning

Autor: Ziko, Imtiaz Masud, Dolz, Jose, Granger, Eric, Ayed, Ismail Ben

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

Zobrazit plný text záznamu

Report

A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses

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

Zobrazit plný text záznamu

Report

Variational Fair Clustering

Autor: Ziko, Imtiaz Masud, Granger, Eric, Yuan, Jing, Ayed, Ismail Ben

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

Zobrazit plný text záznamu

Report

Scalable Laplacian K-modes

Autor: Ziko, Imtiaz Masud, Granger, Eric, Ayed, Ismail Ben

We advocate Laplacian K-modes for joint clustering and density mode finding, and propose a concave-convex relaxation of the problem, which yields a parallel algorithm that scales up to large datasets and high dimensions. We optimize a tight bound (au

Externí odkaz: http://arxiv.org/abs/1810.13044

Zobrazit plný text záznamu

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

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

Publikováno v: CVPR
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

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: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::eee851c248afb91657d14820dea78d69
https://doi.org/10.1109/cvpr46437.2021.01376