Ismail Elezi

papers

628

total citations

papers (14)

Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection

CVPR 2022arXiv

citations

VkD: Improving Knowledge Distillation using Orthogonal Projections

CVPR 2024

citations

Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning

AAAI 2024arXiv

citations

Learning to Discover and Detect Objects

NEURIPS 2022arXiv

citations

The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes

NEURIPS 2022arXiv

citations

From Attention to Activation: Unraveling the Enigmas of Large Language Models

ICLR 2025arXiv

citations

G3DR: Generative 3D Reconstruction in ImageNet

CVPR 2024arXiv

citations

``Principal Components" Enable A New Language of Images

ICCV 2025

citations

Fractal Calibration for Long-tailed Object Detection

CVPR 2025arXiv

citations

Region-based Cluster Discrimination for Visual Representation Learning

ICCV 2025arXiv

citations

Ismail Elezi

papers (14)

CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

Active Learning for Deep Object Detection via Probabilistic Modeling

Simple Cues Lead to a Strong Multi-Object Tracker

The Group Loss for Deep Metric Learning

Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection

VkD: Improving Knowledge Distillation using Orthogonal Projections

Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning

Learning to Discover and Detect Objects

The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes

From Attention to Activation: Unraveling the Enigmas of Large Language Models

G3DR: Generative 3D Reconstruction in ImageNet

``Principal Components" Enable A New Language of Images

Fractal Calibration for Long-tailed Object Detection

Region-based Cluster Discrimination for Visual Representation Learning

papers (14)

CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks

Active Learning for Deep Object Detection via Probabilistic Modeling

Simple Cues Lead to a Strong Multi-Object Tracker

The Group Loss for Deep Metric Learning

Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection

VkD: Improving Knowledge Distillation using Orthogonal Projections

Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning

Learning to Discover and Detect Objects

The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes

From Attention to Activation: Unraveling the Enigmas of Large Language Models

G3DR: Generative 3D Reconstruction in ImageNet

``Principal Components" Enable A New Language of Images

Fractal Calibration for Long-tailed Object Detection

Region-based Cluster Discrimination for Visual Representation Learning