FR2.M1.2
RSAD-CLIP: ZERO-SHOT REMOTE SENSING ANOMALY DETECTION OF THE EARTH’S SURFACE BASED ON PRE-TRAINED VISION-LANGUAGE MODEL
Yu Zhang, Zhi Gao, Wuhan University, China
Session:
FR2.M1: Deep Learning and Remote Sensing for Rapid Disaster Response II Oral
Track:
Community-Contributed Sessions
Location:
Mezzanine: Room M1
Presentation Time:
Friday, 8 August, 10:45 - 11:00
Session Co-Chairs:
Nina Merkle, German Aerospace Center (DLR) and Tanvir Anjum, University of Georgia
Session FR2.M1
FR2.M1.1: ENHANCING DEEP LEARNING PERFORMANCE ON BURNED AREA DELINEATION FROM SPOT-6/7 IMAGERY FOR EMERGENCY MANAGEMENT
María Rodríguez, Minh-Tan Pham, IRISA-Université Bretagne Sud, France; Martin Sudmanns, University of Salzburg, Austria; Quentin Poterek, Oscar Narvaez, ICube-SERTIT, Université de Strasbourg, France
FR2.M1.2: RSAD-CLIP: ZERO-SHOT REMOTE SENSING ANOMALY DETECTION OF THE EARTH’S SURFACE BASED ON PRE-TRAINED VISION-LANGUAGE MODEL
Yu Zhang, Zhi Gao, Wuhan University, China
FR2.M1.3: A DEEP LEARNING SYSTEM FOR BUILDING DAMAGE ASSESSMENT USING VHR COSMO-SKYMED IMAGERY FOR THE 2023 KAHRAMANMARAŞ EARTHQUAKE
Luigi Russo, University of Pavia, Italy; Deodato Tapete, Italian Space Agency (ASI), Italy; Silvia Liberata Ullo, University of Sannio, Italy; Paolo Gamba, University of Pavia, Italy
FR2.M1.4: ADVANCED POST-EARTHQUAKE BUILDING DAMAGE ASSESSMENT: SAR COHERENCE TIME MATRIX WITH VISION TRANSFORMER
Yanchen Yang, Chou Xie, Bangsen Tian, Yihong Guo, Yu Zhu, Shuaichen Bian, Ying Yang, Ming Zhang, Yimin Ruan, Aerospace Information Research Institute, Chinese Academy of Science, China
FR2.M1.5: FREQCROSS: REAL-TIME UAV DISASTER ASSESSMENT VIA FREQUENCY-GUIDED CROSS-DECODER DISTILLATION
Jianchong Guo, Yuting Wan, Ailong Ma, Yanfei Zhong, Wuhan University, China
Resources