Research Associate | Full Stack Developer | Web Scraping and Automation Expert | Certified DL & ML Specialist Muhammad Muqsit Islam is a full-stack developer proficient in Web Development, Computer Vision, and Deep Learning. They are skilled in Django, Django Rest Framework, React, Flask, TensorFlow, Docker and other technologies, effectively bridging the gap between frontend…
M. Wadood Islam was an MS-CS student at LUMS and a Graduate Research Assistant at Computer Vision and Graphics Lab (CVGL), LUMS Syed Babar Ali School of Science and Engineering. He earned his undergraduate degree from FAST-NUCES in Computer Science. His research interests include machine learning, deep learning, computer vision, and bioinformatics. He worked on classifying…
Shehryar Malik, Muhammad Umair Haider*, Omer Iqbal, Murtaza Taj Abstract: Network pruning reduces the size of neural networks by removing (pruning) neurons such that the performance drop is minimal. Traditional pruning approaches focus on designing metrics to quantify the usefulness of a neuron which is often quite tedious and sub-optimal. More recent approaches have instead…
Talha Hanif Butt, Murtaza Taj Abstract: Camera calibration is a necessity in various tasks including 3D reconstruction, hand-eye coordination for a robotic interaction, autonomous driving, etc. In this work we propose a novel method to predict extrinsic (baseline, pitch, and translation), intrinsic (focal length and principal point offset) parameters using an image pair. Unlike existing…
Shaiq Munir Malik, Fnu Mohbat, Muhammad Umair Haider, Muhammad Musab Rasheed and Murtaza Taj Abstract: To reduce the overwhelming size of Deep Neural Networks, teacher-student techniques aim to transfer knowledge from a complex teacher network to a simple student network. We instead propose a novel method called the teacher-class network consisting of a single teacher…
M. U. Qadeer, S. Saeed, M. Taj and A. Muhammad Abstract: Large-area crop classification using multi-spectral imagery is a widely studied problem for several decades and is generally addressed using classical Random Forest classifier. Recently, deep convolutional neural networks (DCNN) have been proposed. However, these methods only achieved results comparable with Random Forest. In this…
Muhammad Umair Haider and Murtaza Taj Abstract: One of the major challenges in deploying deep neural network architectures is their size which has an adverse effect on their inference time and memory requirements. Deep CNNs can either be pruned width-wise by removing filters or depth-wise by removing layers and blocks. Width wise pruning (filter pruning)…
Mohbat Tharani, Abdul Wahab Amin, Fezan Rasool, Muhammad Maaz, Murtaza Taj, Abubakr Muhammad Summary In the absence of an effective trash management framework, trash is often illegally dumped in rivers and canals running through urban areas, contaminating freshwater and blocking drainage lines which result in urban floods. When this contaminated water reaches agricultural fields, it…
Tuberculosis Diagnosis in Medical Imagery using Deep Learning by Inam Ullah Taj Estimating labor population in Brick Kilns using Satellite Imagery and Remote Sensing by Muhammad Awais Ather Compressing neural networks via teacher assisted learning by Umair Haider Online structured filter pruning for neural networks by Shaiq Munir Malik Semantic Segmentation of water channel to…
Numan Khurshid, Mohbat Tharani, Murtaza Taj, and Faisal Qureshi Abstract: We propose a new method for remote sensing image matching. The proposed method uses encoder subnetwork of an autoencoder pre-trained on GTCrossView data to construct image features. A discriminator network trained on University of California Merced Land Use/Land Cover dataset (LandUse) and High-resolution Satellite Scene…
