Mehak Maqbool Memon

Papers

Total Citations

H-Index

About

Mehak Maqbool Memon is a rising researcher in computer vision and deep learning, whose work focuses on advancing semantic segmentation under challenging visual conditions. Her most-cited paper, "Unified DeepLabV3+ for Semi-Dark Image Semantic Segmentation" (2022, 15 citations), addresses the critical but underexplored problem of accurate pixel-level classification in low-light environments. By adapting the DeepLabV3+ architecture—traditionally optimized for well-lit scenes—Memon developed a unified framework that enhances visual perception for autonomous systems and surveillance applications. Her research tackles fundamental challenges in learning deep convolutional neural networks, particularly ResNet-based architectures, for dynamic scene understanding. Beyond this flagship work, Memon's contributions extend to improving model robustness against illumination variations, a key bottleneck in real-world deployment of computer vision systems. Her work has been cited by peers exploring domain adaptation and nighttime scene parsing, demonstrating its relevance to both theoretical and applied research. As an emerging voice in the field, Memon continues to push the boundaries of what deep learning models can achieve in non-ideal imaging conditions, making her research essential reading for students and engineers working on autonomous driving, robotics, and intelligent monitoring systems.