Muhammad Ferjad Naeem

I am a Ph.D. Candidate at the Computer Vision lab at ETH Zürich supervised by Prof. Luc Van Gool and PD. Dr. Federico Tombari. As part of my PhD, supported by a Google fellowship, I work as a Research Consultant with Google in Zurich. I also closely collaborate with Google Deepmind on Foundational Vision Language Models. I am interested in building strong multimodal foundational models. I am also interested in distilling the world knowledge of foundational models to smaller task specific models that can adapt and generalize to novel classes and environments. Previously I obtained my Master's degree from the Technical University of Munich with a focus on Generative Models at Naver AI Lab and Zero-shot Learning at UniTübingen AI Research. I have also been an intern at Nvidia.

Having completed my PhD requirements, I am now on the job market. I am looking for Research Scientist roles focused on building strong foundational models and using them to solve various downstream tasks.

Email / Google Scholar / Github / Twitter / CV

Publications

	SILC: Improving vision language pretraining with self-distillation Muhammad Ferjad Naeem, Yongqin Xian, Xiaohua Zhai, Lukas Hoyer, Luc Van Gool, Federico Tombari arxiv, 2024 Paper
	I2DFormer+: Learning Image to Document Summary Attention for Zero-Shot Image Muhammad Ferjad Naeem, Yongqin Xian, Luc Van Gool, Federico Tombari IJCV, 2024
	Learning to Prompt with Text Only Supervision for Vision-Language Models Muhammad Uzair Khattak, Muhammad Ferjad Naeem, Muzammal Naseer, Luc Van Gool, Federico Tombari arxiv, 2024 Paper / Project Page / Code
	SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance Lukas Hoyer, David Joseph Tan, Muhammad Ferjad Naeem, Luc Van Gool, Federico Tombari arxiv, 2024 Paper / Code
	Introducing Language Guidance in Prompt-based Continual Learning Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal ICCV, 2023 Paper
	I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification Muhammad Ferjad Naeem, Muhammad Gul Zain Ali Khan, Yongqin Xian, Muhammad Zeshan Afzal, Didier Stricker, Luc Van Gool, Federico Tombari CVPR, 2023 Highlight paper (top 2.5%) Paper / Code
	Learning Attention Propagation for Compositional Zero-Shot Learning Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal WACV, 2023
	I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification Muhammad Ferjad Naeem, Yongqin Xian, Luc Van Gool, Federico Tombari NeurIPS, 2022 Paper / Code
	3D Compositional Zero-shot Learning with DeCompositional Consensus Muhammad Ferjad Naeem, Evin Pinar Ornek, Yongqin Xian, Luc Van Gool, Federico Tombari Equal contribution ECCV*, 2022 Paper / Code
	Learning Graph Embeddings for Open World Compositional Zero-shot Learning Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian, Zeynep Akata TPAMI, 2022 Paper / Code
	Learning Graph Embeddings for Compositional Zero-shot Learning Muhammad Ferjad Naeem, Yongqin Xian, Federico Tombari, Zeynep Akata CVPR, 2021 Paper / Code
	Open World Compositional Zero-Shot Learning Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian, Zeynep Akata Equal contribution CVPR*, 2021 Paper / Code
	Reliable Fidelity and Diversity Metrics for Generative Models Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi, Jaejun Yoo Equal contribution ICML*, 2020 Paper / Code / Youtube
	Deep Learning Under the Microscope: Improving the Interpretability of Medical Imaging Neural Networks Magdalini Paschali, Muhammad Ferjad Naeem, Walter Simson, Katja Steiger, Martin Mollenhauer, Nassir Navab Equal contribution Arxiv*, 2019 Paper
	A Multi-Faceted OCR Framework for Artificial Urdu News Ticker Text Recognition Sami-Ur-Rehman, Burhan Ul Tayyab, Muhammad Ferjad Naeem, Adnan Ul-Hasan, Faisal Shafait DAS, 2018 Paper
	Impact of Ligature Coverage on Training Practical Urdu OCR Systems Muhammad Ferjad Naeem, Noor ul Sehr Zia, Aqsa Ahmed Awan, Faisal Shafait, Adnan ul Hasan ICDAR, 2017 Paper

Link of the template