Back to Research
2026

Comparative Study of CNN Architectures on Image Classification

Ali Hamza, supervised by Dr. Sami Ullah , GCUF

ABSTRACT

This paper presents a comprehensive framework for real-time semantic segmentation using attention-based feature fusion. We address the challenge of processing high-resolution images in real-time while maintaining accuracy.

INTRODUCTION

Semantic segmentation is a fundamental task in computer vision with applications in autonomous driving, medical imaging, and robotics. However, achieving both high accuracy and real-time performance remains challenging.