15 citations · 23 across the 14 of their papers we have counts for
16 papers
ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection
Romain Hermary, Samet Hicsonmez, Dan Pineau +2
Time-series anomaly detection (TSAD) is critical in domains such as industrial monitoring, healthcare, and cybersecurity, but it remains challenging due to rare and heterogeneous a…
Annotation Free Spacecraft Detection and Segmentation using Vision Language Models
Samet Hicsonmez, Jose Sosa, Dan Pineau +4
Vision Language Models (VLMs) have demonstrated remarkable performance in open-world zero-shot visual recognition. However, their potential in space-related applications remains la…
Training Free Zero-Shot Visual Anomaly Localization via Diffusion Inversion
Samet Hicsonmez, Abd El Rahman Shabayek, Djamila Aouada
Zero-Shot image Anomaly Detection (ZSAD) aims to detect and localise anomalies without access to any normal training samples of the target data. While recent ZSAD approaches levera…
VLMDiff: Leveraging Vision-Language Models for Multi-Class Anomaly Detection with Diffusion
Samet Hicsonmez, Abd El Rahman Shabayek, Djamila Aouada
Detecting visual anomalies in diverse, multi-class real-world images is a significant challenge. We introduce \ours, a novel unsupervised multi-class visual anomaly detection frame…
Domain Adaptive Object Detection for Space Applications with Real-Time Constraints
Samet Hicsonmez, Abd El Rahman Shabayek, Arunkumar Rathinam +1
Object detection is essential in space applications targeting Space Domain Awareness and also applications involving relative navigation scenarios. Current deep learning models for…
Bridging the Synthetic-Real Gap: Supervised Domain Adaptation for Robust Spacecraft 6-DoF Pose Estimation
Inder Pal Singh, Nidhal Eddine Chenni, Abd El Rahman Shabayek +2
Spacecraft Pose Estimation (SPE) is a fundamental capability for autonomous space operations such as rendezvous, docking, and in-orbit servicing. Hybrid pipelines that combine obje…
Motion Aware ViT-based Framework for Monocular 6-DoF Spacecraft Pose Estimation
Jose Sosa, Dan Pineau, Arunkumar Rathinam +2
Monocular 6-DoF pose estimation plays an important role in multiple spacecraft missions. Most existing pose estimation approaches rely on single images with static keypoint localis…
Zero-Shot Anomaly Detection in Battery Thermal Images Using Visual Question Answering with Prior Knowledge
Marcella Astrid, Abdelrahman Shabayek, Djamila Aouada
Batteries are essential for various applications, including electric vehicles and renewable energy storage, making safety and efficiency critical concerns. Anomaly detection in bat…
Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbation
Romain Hermary, Vincent Gaudillière, Abd El Rahman Shabayek +1
One-class anomaly detection aims to detect objects that do not belong to a predefined normal class. In practice training data lack those anomalous samples; hence state-of-the-art m…
Hybrid Attention for Robust RGB-T Pedestrian Detection in Real-World Conditions
Arunkumar Rathinam, Leo Pauly, Abd El Rahman Shabayek +4
Multispectral pedestrian detection has gained significant attention in recent years, particularly in autonomous driving applications. To address the challenges posed by adversarial…
Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity
Nilotpal Sinha, Peyman Rostami, Abd El Rahman Shabayek +2
Hardware-aware Neural Architecture Search approaches (HW-NAS) automate the design of deep learning architectures, tailored specifically to a given target hardware platform. Yet, th…
Hardware Aware Evolutionary Neural Architecture Search using Representation Similarity Metric
Nilotpal Sinha, Abd El Rahman Shabayek, Anis Kacem +3
Hardware-aware Neural Architecture Search (HW-NAS) is a technique used to automatically design the architecture of a neural network for a specific task and target hardware. However…
Impact of Disentanglement on Pruning Neural Networks
Carl Shneider, Peyman Rostami, Anis Kacem +3
Deploying deep learning neural networks on edge devices, to accomplish task specific objectives in the real-world, requires a reduction in their memory footprint, power consumption…
Face-GCN: A Graph Convolutional Network for 3D Dynamic Face Identification/Recognition
Konstantinos Papadopoulos, Anis Kacem, Abdelrahman Shabayek +1
Face identification/recognition has significantly advanced over the past years. However, most of the proposed approaches rely on static RGB frames and on neutral facial expressions…
A survey on Deep Learning Advances on Different 3D Data Representations
Eman Ahmed, Alexandre Saint, Abd El Rahman Shabayek +5
3D data is a valuable asset the computer vision filed as it provides rich information about the full geometry of sensed objects and scenes. Recently, with the availability of both…
Automatic Classification of Bright Retinal Lesions via Deep Network Features
Ibrahim Sadek, Mohamed Elawady, Abd El Rahman Shabayek
The diabetic retinopathy is timely diagonalized through color eye fundus images by experienced ophthalmologists, in order to recognize potential retinal features and identify early…