YOLO-AMC enhances crack detection with attention mechanisms

Researchers have developed YOLO-AMC, an enhanced YOLO architecture incorporating attention mechanisms for improved building crack detection. This model integrates Global Attention Mechanism (GAM), Residual Convolutional Block Attention Module (Res-CBAM), and Shuffle Attention (SA) into its feature fusion layers. Experiments show YOLO-AMC surpasses baseline models like YOLOv11 and YOLOv8, with GAM achieving the highest performance metrics. AI

IMPACT This research offers a more accurate and efficient method for automated crack detection in infrastructure, potentially improving structural health monitoring.

RANK_REASON The cluster describes a new research paper detailing an improved YOLO architecture for a specific computer vision task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• Global Attention Mechanism (GAM)
• NVIDIA RTX 4090
• Raspberry Pi 5
• Residual Convolutional Block Attention Module (Res-CBAM)
• Shuffle Attention (SA)
• YOLO-AMC
• YOLOv11
• YOLOv8n

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →