AIConfPaper
← Search

Muhammad Ferjad Naeem

12 accepted papers

2025

Active Data Curation Effectively Distills Large-Scale Multimodal Models

Vishaal Udandarao, Nikhil Parthasarathy, Muhammad Ferjad Naeem, Talfan Evans, Samuel Albanie, Federico Tombari +3
CVPR 2025poster

Knowledge distillation (KD) is the de facto standard for compressing large-scale models into smaller ones. Prior works have explored ever more complex KD strategies involving different objective functions, teacher-ensembles, and weight inheritance. In this work we explore an alternative, yet simple…

Cited by 6Source ↗PDF ↗Scholar ↗
2025

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

Muhammad Uzair Khattak, Muhammad Ferjad Naeem, Muzammal Naseer, Luc Van Gool, Federico Tombari
AAAI 2025technical

Foundational vision-language models like CLIP are emerging as a promising paradigm in vision due to their excellent generalization. However, adapting these models for downstream tasks while maintaining their generalization remains challenging. In literature, one branch of methods adapts CLIP by lear…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2025

TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

Haiyang Wang, Yue Fan, Muhammad Ferjad Naeem, Yongqin Xian, Jan Eric Lenssen, Liwei Wang +2
ICLR 2025spotlight

Transformers have become the predominant architecture in foundation models due to their excellent performance across various domains. However, the substantial cost of scaling these models remains a significant concern. This problem arises primarily from their dependence on a fixed number of paramete…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2024

GiT: Towards Generalist Vision Transformer through Universal Language Interface

Haiyang Wang*, Hao Tang, Li Jiang, Shaoshuai Shi, Muhammad Ferjad Naeem, Hongsheng Li +2
ECCV 2024oral

"This paper proposes a simple, yet effective framework, called , simultaneously applicable for various vision tasks only with a vanilla ViT. Motivated by the universality of the Multi-layer Transformer architecture (e.g., GPT) widely used in large language models (LLMs), we seek to broaden its scope…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗
2024

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

Lukas Hoyer*, David Joseph Tan, Muhammad Ferjad Naeem, Luc Van Gool, Federico Tombari
ECCV 2024poster

"In semi-supervised semantic segmentation, a model is trained with a limited number of labeled images along with a large corpus of unlabeled images to reduce the high annotation effort. While previous methods are able to learn good segmentation boundaries, they are prone to confuse classes with simi…

Cited by 24Source ↗PDF ↗code ↗Scholar ↗
2023

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 +1
CVPR 2023highlight

Recent works have shown that unstructured text (documents) from online sources can serve as useful auxiliary information for zero-shot image classification. However, these methods require access to a high-quality source like Wikipedia and are limited to a single source of information. Large Language…

Cited by 74Source ↗PDF ↗code ↗Scholar ↗
2023

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 2023poster

Continual Learning aims to learn a single model on a sequence of tasks without having access to data from previous tasks. The biggest challenge in the domain still remains catastrophic forgetting: a loss in performance on seen classes of earlier tasks. Some existing methods rely on an expensive repl…

Cited by 56PDF ↗code ↗Scholar ↗
2022

3D Compositional Zero-Shot Learning with DeCompositional Consensus

Muhammad Ferjad Naeem, Evin Pınar Örnek, Yongqin Xian, Luc Van Gool, Federico Tombari
ECCV 2022poster

"Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. Towards this, we present 3D Compositional Zero-shot Learning as a problem of part generalization from seen to unseen obje…

Cited by 15Source ↗PDF ↗Scholar ↗
2022

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

Muhammad Ferjad Naeem, Yongqin Xian, Luc Van Gool, Federico Tombari
NeurIPS 2022accept

Despite the tremendous progress in zero-shot learning (ZSL), the majority of existing methods still rely on human-annotated attributes, which are difficult to annotate and scale. An unsupervised alternative is to represent each class using the word embedding associated with its semantic class name.…

Cited by 55Source ↗PDF ↗Scholar ↗
2021

Learning Graph Embeddings for Compositional Zero-Shot Learning

Muhammad Ferjad Naeem, Yongqin Xian, Federico Tombari, Zeynep Akata
CVPR 2021poster

In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog)in the training set. This is challenging because the same state can for example alter the visual appearance of a dog drast…

Cited by 199PDF ↗code ↗Scholar ↗
2021

Open World Compositional Zero-Shot Learning

Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian, Zeynep Akata
CVPR 2021poster

Compositional Zero-Shot learning (CZSL) requires to recognize state-object compositions unseen during training. In this work, instead of assuming prior knowledge about the unseen compositions, we operate in the open world setting, where the search space includes a large number of unseen compositions…

Cited by 168PDF ↗code ↗Scholar ↗
2020

Reliable Fidelity and Diversity Metrics for Generative Models

Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi, Jaejun Yoo
ICML 2020poster

Devising indicative evaluation metrics for the image generation task remains an open problem. The most widely used metric for measuring the similarity between real and generated images has been the Frechet Inception Distance (FID) score. Since it does not differentiate the fidelity and diversity asp…

Cited by 450Source ↗PDF ↗code ↗Scholar ↗