6 papers
A Tutorial on ALOS2 SAR Utilization: Dataset Preparation, Self-Supervised Pretraining, and Semantic Segmentation
Nevrez Imamoglu, Ali Caglayan, Toru Kouyama
Masked auto-encoders (MAE) and related approaches have shown promise for satellite imagery, but their application to synthetic aperture radar (SAR) remains limited due to challenge…
Enhanced LULC Segmentation via Lightweight Model Refinements on ALOS-2 SAR Data
Ali Caglayan, Nevrez Imamoglu, Toru Kouyama
This work focuses on national-scale land-use/land-cover (LULC) semantic segmentation using ALOS-2 single-polarization (HH) SAR data over Japan, together with a companion binary wat…
Exploring Object-Aware Attention Guided Frame Association for RGB-D SLAM
Ali Caglayan, Nevrez Imamoglu, Oguzhan Guclu +3
Attention models have recently emerged as a powerful approach, demonstrating significant progress in various fields. Visualization techniques, such as class activation mapping, pro…
Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360-Degree Videos
Mert Cokelek, Halit Ozsoy, Nevrez Imamoglu +4
Omnidirectional videos (ODVs) are redefining viewer experiences in virtual reality (VR) by offering an unprecedented full field-of-view (FOV). This study extends the domain of sali…
SAR-W-MixMAE: SAR Foundation Model Training Using Backscatter Power Weighting
Ali Caglayan, Nevrez Imamoglu, Toru Kouyama
Foundation model approaches such as masked auto-encoders (MAE) or its variations are now being successfully applied to satellite imagery. Most of the ongoing technical validation o…
A Vision-Language Framework for Multispectral Scene Representation Using Language-Grounded Features
Enes Karanfil, Nevrez Imamoglu, Erkut Erdem +1
Scene understanding in remote sensing often faces challenges in generating accurate representations for complex environments such as various land use areas or coastal regions, whic…