Yakup Genc

Prof. Dr. Yakup Genc

orcid

Research Focus & Metrics

Academic Career Length

26Years (2001-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2021 in Knowledge-Based Systems
Verified
Journal Article
Closed access
MHMohamed Abbas Hedjazi
Mohamed Abbas Hedjazi
YGYakup Genc
Yakup Genc

28 November 2018 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
MDMuhammet Ali Dede
Muhammet Ali Dede
EAErchan Aptoula
Erchan Aptoula
YGYakup Genc
Yakup Genc

25 March 2022 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
IKIkram Kourbane
Ikram Kourbane
YGYakup Genc
Yakup Genc

1 January 2001
Verified
Conference Paper
Open access
YGYakup Genc
Yakup Genc
MTMihran Tuceryan
Mihran Tuceryan
AKA. Khamene
A. Khamene
NNN. Navab
N. Navab

1 February 2007 in IEEE Winter Conference on Applications of Computer Vision (WACV)
Verified
Conference Paper
Closed access
RSRaghav Subbarao
Raghav Subbarao
YGYakup Genc
Yakup Genc
PMPeter Meer
Peter Meer
We propose a new robust estimator for camera pose estimation based on a recently developed nonlinear mean shift algorithm. This allows us to treat pose estimation as a clustering problem in the presence of outliers. We compare our method to RANSAC, which is the standard robust estimator for computer vision problems. We also show that under fairly general assumptions our method is provably better than RANSAC. Synthetic and real examples to support our claims are provided

24 March 2025 in IEEE Access
Verified
Journal Article
Open access
EAEmre Ardıç
Emre Ardıç
YGYakup Genc
Yakup Genc
Federated learning (FL) is a distributed machine learning method where multiple devices collaboratively train a model under the management of a central server without sharing underlying data. One of the key challenges of FL is the communication bottleneck caused by variations in connection speed and bandwidth across devices. Therefore, it is essential to reduce the size of transmitted data during training. Additionally, there is a potential risk of exposing sensitive information through the model or gradient analysis during training. To address both privacy and communication efficiency, we combine differential privacy (DP) and adaptive quantization methods. We use Laplacian-based DP to preserve privacy, which is relatively underexplored in FL and offers tighter privacy guarantees than Gaussian-based DP. We propose a simple and efficient global bit-length scheduler using round-based cosine annealing, along with a client-based scheduler that dynamically adapts based on client contribution estimated through dataset entropy analysis. We evaluate our approach through extensive experiments on CIFAR10, MNIST, and medical imaging datasets, using non-IID data distributions across varying client counts, bit-length schedulers, and privacy budgets. The results show that our adaptive quantization methods reduce total communicated data by up to 52.64% for MNIST, 45.06% for CIFAR10, and 31% to 37% for medical imaging datasets compared to 32-bit float training while maintaining competitive model accuracy and ensuring robust privacy through differential privacy.