Muhammad Ferjad Naeem

papers

731

total citations

papers (11)

Learning Graph Embeddings for Compositional Zero-Shot Learning

CVPR 2021arXiv

180

citations

Open World Compositional Zero-Shot Learning

CVPR 2021arXiv

163

citations

I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification

CVPR 2023arXiv

citations

Introducing Language Guidance in Prompt-based Continual Learning

ICCV 2023arXiv

citations

SILC: Improving Vision Language Pretraining with Self-Distillation

ECCV 2024arXiv

citations

I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

NEURIPS 2022arXiv

citations

Muhammad Ferjad Naeem

papers (11)

Learning Graph Embeddings for Compositional Zero-Shot Learning

Open World Compositional Zero-Shot Learning

I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification

Introducing Language Guidance in Prompt-based Continual Learning

SILC: Improving Vision Language Pretraining with Self-Distillation

I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

Learning to Prompt with Text Only Supervision for Vision-Language Models

SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance

3D Compositional Zero-Shot Learning with DeCompositional Consensus

Active Data Curation Effectively Distills Large-Scale Multimodal Models

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

papers (11)

Learning Graph Embeddings for Compositional Zero-Shot Learning

Open World Compositional Zero-Shot Learning

I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification

Introducing Language Guidance in Prompt-based Continual Learning

SILC: Improving Vision Language Pretraining with Self-Distillation

I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification

Learning to Prompt with Text Only Supervision for Vision-Language Models

SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance

3D Compositional Zero-Shot Learning with DeCompositional Consensus

Active Data Curation Effectively Distills Large-Scale Multimodal Models

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters