6 papers
Synthetic-to-Real Object Detection using YOLOv11 and Domain Randomization Strategies
Luisa Torquato Niño, Hamza A. A. Gardi
This paper addresses the synthetic-to-real domain gap in object detection, focusing on training a YOLOv11 model to detect a specific object (a soup can) using only synthetic data a…
Credit Card Fraud Detection
Iva Popova, Hamza A. A. Gardi
Credit card fraud remains a significant challenge due to class imbalance and fraudsters mimicking legitimate behavior. This study evaluates five machine learning models - Logistic…
Reinforcement Learning Agent for a 2D Shooter Game
Thomas Ackermann, Moritz Spang, Hamza A. A. Gardi
Reinforcement learning agents in complex game environments often suffer from sparse rewards, training instability, and poor sample efficiency. This paper presents a hybrid training…
Evaluating the printability of stl files with ML
Janik Henn, Adrian Hauptmannl, Hamza A. A. Gardi
3D printing has long been a technology for industry professionals and enthusiasts willing to tinker or even build their own machines. This stands in stark contrast to today's marke…
GhostNetV3-Small: A Tailored Architecture and Comparative Study of Distillation Strategies for Tiny Images
Florian Zager, Hamza A. A. Gardi
Deep neural networks have achieved remarkable success across a range of tasks, however their computational demands often make them unsuitable for deployment on resource-constrained…
Linear Dimensionality Reduction for Word Embeddings in Tabular Data Classification
Liam Ressel, Hamza A. A. Gardi
The Engineers' Salary Prediction Challenge requires classifying salary categories into three classes based on tabular data. The job description is represented as a 300-dimensional…