Ismail Ben Ayed

papers

1,308

total citations

papers (28)

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

CVPR 2021arXiv

226

citations

Parameter-Free Online Test-Time Adaptation

CVPR 2022arXiv

203

citations

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

ECCV 2020arXiv

184

citations

The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration

CVPR 2022arXiv

citations

Information Maximization for Few-Shot Learning

NEURIPS 2020arXiv

citations

A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models

CVPR 2024arXiv

citations

On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?

CVPR 2024arXiv

citations

Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation

NEURIPS 2025arXiv

citations

SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds

ICML 2025arXiv

citations

UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning

CVPR 2025arXiv

citations

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses

NEURIPS 2025arXiv

citations

Learning Task-Agnostic Representations through Multi-Teacher Distillation

NEURIPS 2025arXiv

citations

NC-TTT: A Noise Constrastive Approach for Test-Time Training

CVPR 2024

citations

Ismail Ben Ayed

papers (28)

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

Parameter-Free Online Test-Time Adaptation

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

The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration

Information Maximization for Few-Shot Learning

A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models

On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?

Augmented Lagrangian Adversarial Attacks

Realistic evaluation of transductive few-shot learning

LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP

Parametric Information Maximization for Generalized Category Discovery

A Strong Baseline for Generalized Few-Shot Semantic Segmentation

Transductive Zero-Shot and Few-Shot CLIP

Proximal Splitting Adversarial Attack for Semantic Segmentation

ClusT3: Information Invariant Test-Time Training

Robust Calibration of Large Vision-Language Adapters

Open-Set Likelihood Maximization for Few-Shot Learning

AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

Class Adaptive Network Calibration

Spectral Informed Mamba for Robust Point Cloud Processing

Realistic Test-Time Adaptation of Vision-Language Models

Conformal Prediction for Zero-Shot Models

Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation

SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds

UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses

Learning Task-Agnostic Representations through Multi-Teacher Distillation

NC-TTT: A Noise Constrastive Approach for Test-Time Training

papers (28)

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

Parameter-Free Online Test-Time Adaptation

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

The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration

Information Maximization for Few-Shot Learning

A Closer Look at the Few-Shot Adaptation of Large Vision-Language Models

On the Test-Time Zero-Shot Generalization of Vision-Language Models: Do We Really Need Prompt Learning?

Augmented Lagrangian Adversarial Attacks

Realistic evaluation of transductive few-shot learning

LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP

Parametric Information Maximization for Generalized Category Discovery

A Strong Baseline for Generalized Few-Shot Semantic Segmentation

Transductive Zero-Shot and Few-Shot CLIP

Proximal Splitting Adversarial Attack for Semantic Segmentation

ClusT3: Information Invariant Test-Time Training

Robust Calibration of Large Vision-Language Adapters

Open-Set Likelihood Maximization for Few-Shot Learning

AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples

Class Adaptive Network Calibration

Spectral Informed Mamba for Robust Point Cloud Processing

Realistic Test-Time Adaptation of Vision-Language Models

Conformal Prediction for Zero-Shot Models

Test-Time Adaptation of Vision-Language Models for Open-Vocabulary Semantic Segmentation

SMART-PC: Skeletal Model Adaptation for Robust Test-Time Training in Point Clouds

UNEM: UNrolled Generalized EM for Transductive Few-Shot Learning

TRUST: Test-Time Refinement using Uncertainty-Guided SSM Traverses

Learning Task-Agnostic Representations through Multi-Teacher Distillation

NC-TTT: A Noise Constrastive Approach for Test-Time Training