8 papers
CLIP Under the Microscope: A Fine-Grained Analysis of Multi-Object Representation
Reza Abbasi, Ali Nazari, Aminreza Sefid +3
Contrastive Language-Image Pre-training (CLIP) models excel in zero-shot classification, yet face challenges in complex multi-object scenarios. This study offers a comprehensive an…
Analyzing CLIP's Performance Limitations in Multi-Object Scenarios: A Controlled High-Resolution Study
Reza Abbasi, Ali Nazari, Aminreza Sefid +3
Contrastive Language-Image Pre-training (CLIP) models have demonstrated remarkable performance in zero-shot classification tasks, yet their efficacy in handling complex multi-objec…
Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models
Reza Abbasi, Sernam Lim
The rapid growth in machine learning models, especially in natural language processing and computer vision, has led to challenges when running these models on hardware with limited…
Attention Overlap Is Responsible for The Entity Missing Problem in Text-to-image Diffusion Models!
Arash Marioriyad, Mohammadali Banayeeanzade, Reza Abbasi +2
Text-to-image diffusion models, such as Stable Diffusion and DALL-E, are capable of generating high-quality, diverse, and realistic images from textual prompts. However, they somet…
Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models
Reza Abbasi, Mohammad Hossein Rohban, Mahdieh Soleymani Baghshah
CLIP models have recently shown to exhibit Out of Distribution (OoD) generalization capabilities. However, Compositional Out of Distribution (C-OoD) generalization, which is a cruc…
GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models
Ali Abdollahi, Mahdi Ghaznavi, Mohammad Reza Karimi Nejad +6
Vision-language models (VLMs) are intensively used in many downstream tasks, including those requiring assessments of individuals appearing in the images. While VLMs perform well i…
Language Plays a Pivotal Role in the Object-Attribute Compositional Generalization of CLIP
Reza Abbasi, Mohammad Samiei, Mohammad Hossein Rohban +1
Vision-language models, such as CLIP, have shown promising Out-of-Distribution (OoD) generalization under various types of distribution shifts. Recent studies attempted to investig…
Spuriosity Rankings for Free: A Simple Framework for Last Layer Retraining Based on Object Detection
Mohammad Azizmalayeri, Reza Abbasi, Amir Hosein Haji Mohammad rezaie +4
Deep neural networks have exhibited remarkable performance in various domains. However, the reliance of these models on spurious features has raised concerns about their reliabilit…