{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/yolov12-a-breakdown-of-the-key-architectural","title":"YOLOv12: A Breakdown of the Key Architectural Features","arxiv_id":"2502.14740","date":"2025-02-20","proceeding":null,"authors":["Mujadded Al Rabbani Alif","Muhammad Hussain"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2502.14740v1","url_pdf":"https://arxiv.org/pdf/2502.14740v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-object-detection","task_name":"Real-Time Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/real-time-object-detection-on-coco","task":"Real-Time Object Detection","dataset":"COCO (Common Objects in Context)","model":"YOLOv12x","rank_in_archive_order":14,"of":82,"metrics":{"FPS (V100, b=1)":"85 (T4)","box AP":"55.2"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-object-detection-on-coco","task":"Real-Time Object Detection","dataset":"COCO (Common Objects in Context)","model":"YOLOv12l","rank_in_archive_order":28,"of":82,"metrics":{"FPS (V100, b=1)":"148 (T4)","box AP":"53.7"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-object-detection-on-coco","task":"Real-Time Object Detection","dataset":"COCO (Common Objects in Context)","model":"YOLOv12m","rank_in_archive_order":42,"of":82,"metrics":{"FPS (V100, b=1)":"206 (T4)","box AP":"52.5"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-object-detection-on-coco","task":"Real-Time Object Detection","dataset":"COCO (Common Objects in Context)","model":"YOLOv12s","rank_in_archive_order":62,"of":82,"metrics":{"FPS (V100, b=1)":"383 (T4)","box AP":"48.0"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-object-detection-on-coco","task":"Real-Time Object Detection","dataset":"COCO (Common Objects in Context)","model":"YOLOv12n","rank_in_archive_order":76,"of":82,"metrics":{"FPS (V100, b=1)":"610 (T4)","box AP":"40.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2502.14740","atlas_url":"https://app.syntology.ai/?focus=2502.14740","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}