AI Learns When to Switch On Global Attention for Sharper Satellite Maps
Researchers have developed RL-Axial, a segmentation framework that uses reinforcement learning to decide for each image patch whether to apply ...
Researchers have developed RL-Axial, a segmentation framework that uses reinforcement learning to decide for each image patch whether to apply ...
Researchers have unveiled a weakly supervised AI framework that segments crops, weeds and soil from image-level labels alone, achieving 76.04 ...
Researchers in China have developed NERA-Net, a framework that prevents the early loss of spatial details in few-shot semantic segmentation ...
Researchers combined aerial image segmentation and camera-based object detection to build the first corridor-wide, AI-driven indicators of parking supply and ...
Researchers have developed a semi-supervised deep learning method that automatically detects and vectorizes faults and geological boundaries on archived scanned ...
Researchers have developed a two-level evaluation framework showing that synthetic vertebrae which score highly on geometric similarity can still fail ...
Researchers in Morocco have built a real-time pipeline that combines a hybrid U-Net and SegFormer deep learning model with a ...
Researchers in Singapore have developed a semantic object-based descriptor called OSSC that improves loop closure detection for robots, enabling accurate ...
A new RGB-D SLAM system from researchers in China keeps indoor robots accurately localized in dynamic environments by using human ...
Researchers at SLIET Longowal have developed a hybrid AI framework that combines YOLOv8 semantic segmentation with NeuS neural surface reconstruction ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine