55 citations · 122 across the 10 of their papers we have counts for
11 papers
MoP-CLIP: A Mixture of Prompt-Tuned CLIP Models for Domain Incremental Learning
Julien Nicolas, Florent Chiaroni, Imtiaz Ziko +3
Despite the recent progress in incremental learning, addressing catastrophic forgetting under distributional drift is still an open and important problem. Indeed, while state-of-th…
Task Adaptive Feature Transformation for One-Shot Learning
Imtiaz Masud Ziko, Freddy Lecue, Ismail Ben Ayed
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 entro…
Parametric Information Maximization for Generalized Category Discovery
Florent Chiaroni, Jose Dolz, Ziko Imtiaz Masud +2
We introduce a Parametric Information Maximization (PIM) model for the Generalized Category Discovery (GCD) problem. Specifically, we propose a bi-level optimization formulation, w…
Mutual-Information Based Few-Shot Classification
Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony +3
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions fo…
Transductive Few-Shot Learning: Clustering is All You Need?
Imtiaz Masud Ziko, Malik Boudiaf, Jose Dolz +2
We investigate a general formulation for clustering and transductive few-shot learning, which integrates prototype-based objectives, Laplacian regularization and supervision constr…
Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
Malik Boudiaf, Hoel Kervadec, Ziko Imtiaz Masud +3
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…
Transductive Information Maximization For Few-Shot Learning
Malik Boudiaf, Ziko Imtiaz Masud, Jérôme Rony +3
We introduce Transductive Infomation Maximization (TIM) for few-shot learning. Our method maximizes the mutual information between the query features and their label predictions fo…
Laplacian Regularized Few-Shot Learning
Imtiaz Masud Ziko, Jose Dolz, Eric Granger +1
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 f…
A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses
Malik Boudiaf, Jérôme Rony, Imtiaz Masud Ziko +4
Recently, substantial research efforts in Deep Metric Learning (DML) focused on designing complex pairwise-distance losses, which require convoluted schemes to ease optimization, s…
Variational Fair Clustering
Imtiaz Masud Ziko, Eric Granger, Jing Yuan +1
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, includi…
Scalable Laplacian K-modes
Imtiaz Masud Ziko, Eric Granger, Ismail Ben Ayed
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 u…