Compact Aerial Vision Model Refines Features to Improve Small Object Detection
Researchers have developed AeroDet, a lightweight drone-based object detector that improves small-target accuracy in dense aerial traffic by refining internal ...
Researchers have developed AeroDet, a lightweight drone-based object detector that improves small-target accuracy in dense aerial traffic by refining internal ...
Researchers designed the WDA-YOLO detector to improve industrial weld-defect identification through multi-scale feature decoupling, multi-level context fusion, and task-aligned interactive ...
Researchers developed RCE-YOLO to detect surface defects on aerospace transparent components, improving baseline detection metrics while highlighting significant architectural trade-offs ...
Researchers developed FFLE-Net, a lightweight architecture that enhances small object detection in aerial and drone imagery while preserving real-time processing ...
A study evaluating the Agrosense v2 platform reveals that subtle adversarial image perturbations severely degrade deep-learning vision models and corrupt ...
Adding a stride-4 P2 detection branch to YOLOv11n raised tiny fabric defect detection mAP@0.5 by 5.8 percentage points on the ...
Researchers in Norway have developed Hjort-YOLO, a lightweight and explainable AI framework that detects wildlife from camera-trap images faster and ...
A Chinese research team has developed HSM-YOLO, a lightweight deep learning model that detects estrus-related mounting behavior in group-housed sheep ...
A redesigned YOLOv11n network recognizes lying, standing, eating and drinking in dense sheep flocks in real time while running on ...
© 2026 Scienmag - Science Magazine
© 2026 Scienmag - Science Magazine