Mask R-CNN
PulseAugur coverage of Mask R-CNN — every cluster mentioning Mask R-CNN across labs, papers, and developer communities, ranked by signal.
-
New AI method predicts roof geometry and segmentation from aerial images
Researchers have developed a novel method for simultaneously segmenting roof structures in aerial imagery and regressing their geometric attributes. This approach enhances Mask R-CNN with a specialized branch for attrib…
-
AI framework detects methane plumes using satellite data
Researchers have developed a machine learning framework to detect methane plumes from satellite imagery, specifically addressing challenges with limited labeled data from MethaneSAT. The system utilizes a Mask R-CNN mod…
-
Instance Segmentation Advances Pavement Crack Assessment
A new paper details a vision-based system for pavement distress assessment that utilizes Mask R-CNN instance segmentation for precise crack localization. This approach significantly outperforms traditional object detect…
-
CNNs outperform Transformers on tree canopy segmentation with limited data
Researchers investigated the effectiveness of five different deep learning architectures, including YOLOv11, Mask R-CNN, DeepLabv3, Swin-UNet, and DINOv2, for tree canopy segmentation using a very limited dataset of onl…
-
KAYRA AI system offers flexible cloud/on-premise deployment for karyotyping
Researchers have developed KAYRA, a microservice architecture for AI-assisted karyotyping designed for clinical cytogenetic laboratories. The system integrates multiple machine learning models, including semantic segmen…