Publications
Neural Network Pruning Through Constrained Reinforcement Learning
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 […]
Camera Calibration through Camera Projection Loss
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 […]
Teacher-Class Network: A Neural Network Compression Mechanism
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 […]
Spatio-Temporal Crop Classification On Volumetric Data
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 […]
Comprehensive Online Network Pruning via Learnable Scaling Factors
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) […]
Kiln-Net
Usman Nazir, Usman Khalid Mian, Muhammad Usman Sohail, Murtaza Taj and Momin Uppal Abstract: The availability of high-resolution satellite imagery has enabled several new applications. One such application is identification of brick kilns for the elimination of modern day slavery which is also one of UN’s Sustainable Development Goals (SDG). This requires automated analysis of […]
IEEE TGRS – A Residual-Dyad Encoder Discriminator Network for Remote Sensing Image Matching
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 […]
ICIAP 2019 – Dimensionality Reduction Using Discriminative Autoencoders for Remote Sensing Image Retrieval
Mohbat, Tooba Mukhtar, Numan Khurshid, and Murtaza Taj International Conference on Image Analysis and Processing (ICAIP), Trento, Itlay, September 9-13, 2019 Abstract Advancements in deep learning techniques caused a paradigm shift in feature extraction for image perception from handcrafted methods to deep methods. However, these deep features if learned through unsupervised methods bear large memory […]
Statistically Correlated Multi-task Learning for Autonomous Driving
Waseem Abbas, M. Fakhir Khan, Murtaza Taj, and Arif Mahmood Abstract Autonomous driving research is an emerging domain in computer vision and machine learning areas. Most existing methods perform Single Task Learning (STL) from one or more images while Multi-Task Learning (MTL) is more efficient due to the leverage of shared information between different tasks. […]
Tiny-Inception-ResNet-v2: Using Deep Learning for Eliminating Bonded Labors of Brick Kilns in South Asia
Usman Nazir, Numan Khurshid, Muhammad Ahmed Bhimra, Murtaza Taj International Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA, June 16-21, 2019 Abstract This paper proposes to employ a Inception-ResNet inspired deep learning architecture called Tiny-Inception-ResNet-v2 to eliminate bonded labor by identifying brick kilns within “Brick-Kiln-Belt” of South Asia. The framework is developed […]
