remote-sensing imagery
PulseAugur coverage of remote-sensing imagery — every cluster mentioning remote-sensing imagery across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New benchmark and survey advance remote sensing image segmentation
Researchers have introduced VPRef, a new benchmark for referring remote sensing image segmentation designed to address performance degradation caused by visual and textual domain drift. This benchmark, featuring over 46…
-
Diffusion models enhance remote sensing object detection with novel augmentation techniques · 2 sources tracked
Two research papers propose novel methods using diffusion models to enhance few-shot object detection (FSOD) in remote sensing images. The first paper introduces 'Control Copy-Paste,' which injects novel objects into di…
-
New Visual Transformer Enhances Health Prediction Using Geospatial Data
Researchers have developed a novel Geo-Context Guided Visual Transformer (GeoCTR) designed to improve the analysis of remote sensing imagery for health outcome prediction. This model integrates geospatial data by conver…
-
New research uses fANOVA to analyze deep learning model design choices
A new research paper published on arXiv introduces a functional ANOVA (fANOVA) approach to analyze the impact of design choices on deep learning models for multi-label classification of remote sensing imagery. The study…
-
New BRIC-Net improves remote sensing image deshadowing
Researchers have developed BRIC-Net, a novel network designed to improve deshadowing in remote sensing images. This method decouples illumination recovery from chromatic reconstruction by using a Lightness Reliability P…
-
Textual Inversion Enhances Remote Sensing Image Segmentation Accuracy
Researchers have developed a new method for few-shot open-vocabulary segmentation on remote sensing imagery, addressing performance gaps that arise from weak text queries. By using textual inversion on a frozen model, t…
-
DisasterTD framework uses MLLMs and cross-view imagery for disaster geolocalization
Researchers have developed DisasterTD, a framework designed to improve the accuracy of geolocating information from social media during disasters. This system combines the semantic reasoning capabilities of multimodal l…
-
New methods tackle remote sensing visual grounding challenges · 2 sources tracked
Two new research papers introduce novel approaches to remote sensing visual grounding (RSVG), a task that involves locating objects in high-resolution images using natural language descriptions. GeoSearcher employs a tw…
-
Active learning slashes remote sensing annotation costs
Researchers have developed Active-SAOOD, a novel method to reduce the cost of annotating oriented objects in remote sensing images. This active learning approach intelligently selects the most informative sparse samples…