Browsing Computer Science by Author "(ORCID 0000-0002-2069-3807 & YÖK ID 386309) Özer, Sedat"
Now showing items 1-7 of 7
-
InfraGAN: A GAN architecture to transfer visible images to infrared domain
Özkanoglu, M. A.; Özer, Sedat (Elsevier, 2022-03)Utilizing both visible and infrared (IR) images in various deep learning based computer vision tasks has been a recent trend. Consequently, datasets having both visible and IR image pairs are desired in many applications. ... -
Offloading deep learning powered vision tasks from UAV to 5G edge server with denoising
Özer, Sedat; Ilhan, H. E.; Özkanoğlu, Mehmet Akif; Cirpan, H. A. (IEEE, 2023-06)Offloading computationally heavy tasks from an unmanned aerial vehicle (UAV) to a remote server helps improve battery life and can help reduce resource requirements. Deep learning based state-of-the-art computer vision ... -
ORTPiece: An ORT-based Turkish image captioning network based on transformers and WordPiece
Ersoy, Asım; Yıldız, Olcay Taner; Özer, Sedat (IEEE, 2023)Recent transformers-based systems are advancing image captioning applications. However, those works have been mainly applied to English-based image captioning problems. In this paper, we introduce a transformers-based ... -
Performance analysis of meta-learning based bayesian deep kernel transfer methods for regression tasks
Savaşlı, Ahmet Çağatay; Tütüncü, Damla; Ndigande, Alain Patrick; Özer, Sedat (IEEE, 2023)Meta-learning aims to apply existing models on new tasks where the goal is 'learning to learn' so that learning from a limited amount of labeled data or learning in a short amount of time is possible. Deep Kernel Transfer ... -
SiameseFuse: A computationally efficient and a not-so-deep network to fuse visible and infrared images
Özer, Sedat; Ege, M.; Özkanoglu, M. A. (Elsevier, 2022-09)Recent developments in pattern analysis have motivated many researchers to focus on developing deep learning based solutions in various image processing applications. Fusing multi-modal images has been one such application ... -
Using different loss functions with YOLACT++ for real-time instance segmentation
Köleş, Selin; Karakaş, Selami; Ndigande, Alain Patrick; Özer, Sedat (IEEE, 2023)In this paper, we study and analyze the performance of various loss functions on a recently proposed real-time instance segmentation algorithm, YOLACT++. In particular, we study the loss functions, including Huber Loss, ... -
YOLODrone+: improved YOLO architecture for object detection in UAV images
Şahin, Ö.; Özer, Sedat (IEEE, 2022)The performance of object detection algorithms running on images taken from Unmanned Aerial Vehicles (UAVs) remains limited when compared to the object detection algorithms running on ground taken images. Due to its various ...
Share this page