Search Results for author: Sunder Ali Khowaja

Found 17 papers, 2 papers with code

FISTNet: FusIon of STyle-path generative Networks for Facial Style Transfer

no code implementations18 Jul 2023 Sunder Ali Khowaja, Lewis Nkenyereye, Ghulam Mujtaba, Ik Hyun Lee, Giancarlo Fortino, Kapal Dev

In this paper, we propose a FusIon of STyles (FIST) network for facial images that leverages pre-trained multipath style transfer networks to eliminate the problem associated with lack of huge data volume in the training phase along with the fusion of multiple styles at the output.

Style Transfer Transfer Learning

SelfFed: Self-supervised Federated Learning for Data Heterogeneity and Label Scarcity in IoMT

no code implementations4 Jul 2023 Sunder Ali Khowaja, Kapal Dev, Syed Muhammad Anwar, Marius George Linguraru

We perform our experimental analysis on publicly available medical imaging datasets and show that our proposed SelfFed framework performs better when compared to existing baselines concerning non-independent and identically distributed (IID) data and label scarcity.

Federated Learning Self-Supervised Learning

ChatGPT Needs SPADE (Sustainability, PrivAcy, Digital divide, and Ethics) Evaluation: A Review

no code implementations13 Apr 2023 Sunder Ali Khowaja, Parus Khuwaja, Kapal Dev, Weizheng Wang, Lewis Nkenyereye

Furthermore, we also suggest some policies and recommendations for EU AI policy act concerning ethics, digital divide, and sustainability.

Ethics Language Modelling +1

SPIN: Simulated Poisoning and Inversion Network for Federated Learning-Based 6G Vehicular Networks

no code implementations21 Nov 2022 Sunder Ali Khowaja, Parus Khuwaja, Kapal Dev, Angelos Antonopoulos

Vehicular networks have always faced data privacy preservation concerns, which lead to the advent of distributed learning techniques such as federated learning.

Federated Learning Generative Adversarial Network +1

2nd Place Solutions for UG2+ Challenge 2022 -- D$^{3}$Net for Mitigating Atmospheric Turbulence from Images

no code implementations25 Aug 2022 Sunder Ali Khowaja, Ik Hyun Lee, Jiseok Yoon

This technical report briefly introduces to the D$^{3}$Net proposed by our team "TUK-IKLAB" for Atmospheric Turbulence Mitigation in $UG2^{+}$ Challenge at CVPR 2022.

Deblurring Denoising +1

AI and 6G into the Metaverse: Fundamentals, Challenges and Future Research Trends

no code implementations23 Aug 2022 Muhammad Zawish, Fayaz Ali Dharejo, Sunder Ali Khowaja, Kapal Dev, Steven Davy, Nawab Muhammad Faseeh Qureshi, Paolo Bellavista

It is anticipated that Metaverse will be a continuum of rapidly emerging technologies, usecases, capabilities, and experiences that will make it up for the next evolution of the Internet.

Mixed Reality

IIFNet: A Fusion based Intelligent Service for Noisy Preamble Detection in 6G

no code implementations16 Apr 2022 Sunder Ali Khowaja, Kapal Dev, Parus Khuwaja, Quoc-Viet Pham, Nawab Muhammad Faseeh Qureshi, Paolo Bellavista, Maurizio Magarini

We propose an informative instance-based fusion network (IIFNet) to cope with random noise and to improve detection performance, simultaneously.

Towards Energy Efficient Distributed Federated Learning for 6G Networks

no code implementations19 Jan 2022 Sunder Ali Khowaja, Kapal Dev, Parus Khuwaja, Paolo Bellavista

The provision of communication services via portable and mobile devices, such as aerial base stations, is a crucial concept to be realized in 5G/6G networks.

Edge-computing Federated Learning

Get your Foes Fooled: Proximal Gradient Split Learning for Defense against Model Inversion Attacks on IoMT data

no code implementations12 Jan 2022 Sunder Ali Khowaja, Ik Hyun Lee, Kapal Dev, Muhammad Aslam Jarwar, Nawab Muhammad Faseeh Qureshi

However, it has been shown recently that the deep learning networks can be exploited by adversarial attacks that not only make IoMT vulnerable to the data theft but also to the manipulation of medical diagnosis.

Medical Diagnosis

Towards Industrial Private AI: A two-tier framework for data and model security

no code implementations27 Jul 2021 Sunder Ali Khowaja, Kapal Dev, Nawab Muhammad Faseeh Qureshi, Parus Khuwaja, Luca Foschini

We proposed a three-layer encryption method for data security and provide a hypothetical method to secure the model parameters.

Federated Learning

Internet of Everything enabled solution for COVID-19, its new variants and future pandemics: Framework, Challenges, and Research Directions

no code implementations2 Jan 2021 Sunder Ali Khowaja, Parus Khuwaja, Kapal Dev

After affecting the world in unexpected ways, COVID-19 has started mutating which is evident with the insurgence of its new variants.

Triage of Potential COVID-19 Patients from Chest X-ray Images using Hierarchical Convolutional Networks

no code implementations1 Nov 2020 Kapal Dev, Sunder Ali Khowaja, Ankur Singh Bist, Vaibhav Saini, Surbhi Bhatia

The HCN uses the first convolution layer from COVIDNet followed by the convolutional layers from well-known pre-trained networks to extract the features.

Binary Classification

Semantic Image Networks for Human Action Recognition

no code implementations21 Jan 2019 Sunder Ali Khowaja, Seok-Lyong Lee

We also propose the sequential combination of Inception-ResNetv2 and long-short-term memory network (LSTM) to leverage the temporal variances for improved recognition performance.

Action Recognition Clustering +1

Cannot find the paper you are looking for? You can Submit a new open access paper.