3 papers
cs.CV2026
Training-Free Multi-Concept LoRA Composition with Prompt-Aware Weighting
Georgios Tsoumplekas, Stella Bounareli, Vasileios Argyriou
Low-Rank Adaptation (LoRA) successfully enables personalization in text-to-image generation by adapting pre-trained diffusion models to specific visual concepts and styles. However…
cs.CV2024
A Closer Look at Data Augmentation Strategies for Finetuning-Based Low/Few-Shot Object Detection
Vladislav Li, Georgios Tsoumplekas, Ilias Siniosoglou +4
Current methods for low- and few-shot object detection have primarily focused on enhancing model performance for detecting objects. One common approach to achieve this is by combin…
cs.LG2024
Enhancing Performance for Highly Imbalanced Medical Data via Data Regularization in a Federated Learning Setting
Georgios Tsoumplekas, Ilias Siniosoglou, Vasileios Argyriou +2
The increased availability of medical data has significantly impacted healthcare by enabling the application of machine / deep learning approaches in various instances. However, me…