Papers › YOLOv12: A Breakdown of the Key Architectural Features

YOLOv12: A Breakdown of the Key Architectural Features

20 Feb 2025arXiv:2502.14740archive 2025-07-28

Mujadded Al Rabbani Alif, Muhammad Hussain

This paper presents an architectural analysis of YOLOv12, a significant advancement in single-stage, real-time object detection building upon the strengths of its predecessors while introducing key improvements. The model incorporates an optimised backbone (R-ELAN), 7x7 separable convolutions, and FlashAttention-driven area-based attention, improving feature extraction, enhanced efficiency, and robust detections. With multiple model variants, similar to its predecessors, YOLOv12 offers scalable solutions for both latency-sensitive and high-accuracy applications. Experimental results manifest consistent gains in mean average precision (mAP) and inference speed, making YOLOv12 a compelling choice for applications in autonomous systems, security, and real-time analytics. By achieving an optimal balance between computational efficiency and performance, YOLOv12 sets a new benchmark for real-time computer vision, facilitating deployment across diverse hardware platforms, from edge devices to high-performance clusters.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational EfficiencyObject DetectionReal-Time Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12x FPS (V100, b=1) 85 (T4) #14 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12x box AP 55.2 #14 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12l FPS (V100, b=1) 148 (T4) #28 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12l box AP 53.7 #28 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12m FPS (V100, b=1) 206 (T4) #42 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12m box AP 52.5 #42 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12s FPS (V100, b=1) 383 (T4) #62 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12s box AP 48.0 #62 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12n FPS (V100, b=1) 610 (T4) #76 of 82 Archive leaderboard report
Real-Time Object Detection COCO (Common Objects in Context) YOLOv12n box AP 40.6 #76 of 82 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections