MO4.M2.3
SAR-W-MIXMAE: SAR FOUNDATION MODEL TRAINING USING BACKSCATTER POWER WEIGHTING
Ali Caglayan, Nevrez Imamoglu, Toru Kouyama, National Institute of Advanced Industrial Science and Technologhy, Japan
Session:
MO4.M2: Advancements in Deep Learning for SAR Remote Sensing Applications II Oral
Track:
Community-Contributed Sessions
Location:
Room M2
Presentation Time:
Monday, 4 August, 16:15 - 16:30
Session Co-Chairs:
Shubham Awasthi, and Gunjan Joshi, HZDR
Presentation
Discussion
Resources
No resources available.
Session MO4.M2
MO4.M2.1: SYNTHESIS OF COMPLEX-VALUED INSAR DATA WITH A MULTI-TASK CONVOLUTIONAL NEURAL NETWORK
Philipp Sibler, Francescopaolo Sica, Michael Schmitt, University of the Bundeswehr Munich, Germany
MO4.M2.2: A Deep Learning based Solution for Persistent Scatterers Detection
Weili Tang, University of Naples, Italy; Simona Verde, National Research Council (CNR), Italy; Sergio Vitale, Vito Pascazio, University of Napoli “Parthenope”, Italy; Gianfranco Fornaro, National Research Council (CNR), Italy
MO4.M2.3: SAR-W-MIXMAE: SAR FOUNDATION MODEL TRAINING USING BACKSCATTER POWER WEIGHTING
Ali Caglayan, Nevrez Imamoglu, Toru Kouyama, National Institute of Advanced Industrial Science and Technologhy, Japan
MO4.M2.4: MULTI-VIEW SAR TARGET RECOGNITION BASED ON SEMANTIC-VIEW DUAL-BRANCH FEATURE EMBEDDING FUSION NETWORK
Haochuan Wang, Wei Yang, Hongcheng Zeng, Bing Sun, Chunsheng Li, Guanhe Lin, Beihang University, China
MO4.M2.5: Deep Learning Augmentations for InSAR Volcanic Deformation Detection
Teo Beker, German Aerospace Center, Germany; Xiao Xiang Zhu, Technical University of Munich, Germany
Resources
No resources available.