Potsdam
PulseAugur coverage of Potsdam — every cluster mentioning Potsdam across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
GMBFormer improves urban green-space extraction with NDVI-guided memory bank
Researchers have developed GMBFormer, a new Transformer-based framework designed to improve the extraction of urban green spaces from ultra-high-resolution imagery. This model utilizes Normalized Difference Vegetation I…
-
New training strategy improves multimodal segmentation with missing data
Researchers have developed a new training strategy for multimodal semantic segmentation that addresses the challenge of missing sensor modalities. This method learns to sample modality availability scenarios directly fr…
-
Remote SAMsing: From Segment Anything to Segment Everything
Researchers have developed an open-source pipeline called Remote SAMsing to improve the segmentation capabilities of the SAM2 model for remote sensing imagery. The pipeline addresses challenges such as the quality-cover…
-
New pre-training strategy boosts deep learning accuracy in remote sensing image segmentation
Researchers have developed a new pre-training strategy for deep learning models used in semantic segmentation of remotely sensed images. This method aims to mitigate performance degradation caused by domain gaps between…