{"work":{"id":"b2da2ba7-83b7-4573-96e5-d6f2b8ef3897","openalex_id":null,"doi":null,"arxiv_id":"2502.12524","raw_key":null,"title":"YOLOv12: Attention-Centric Real-Time Object Detectors","authors":null,"authors_text":"Yunjie Tian, Qixiang Ye, David Doermann","year":2025,"venue":"cs.CV","abstract":"Enhancing the network architecture of the YOLO framework has been crucial for a long time, but has focused on CNN-based improvements despite the proven superiority of attention mechanisms in modeling capabilities. This is because attention-based models cannot match the speed of CNN-based models. This paper proposes an attention-centric YOLO framework, namely YOLOv12, that matches the speed of previous CNN-based ones while harnessing the performance benefits of attention mechanisms. YOLOv12 surpasses all popular real-time object detectors in accuracy with competitive speed. For example, YOLOv12-N achieves 40.6% mAP with an inference latency of 1.64 ms on a T4 GPU, outperforming advanced YOLOv10-N / YOLOv11-N by 2.1%/1.2% mAP with a comparable speed. This advantage extends to other model scales. YOLOv12 also surpasses end-to-end real-time detectors that improve DETR, such as RT-DETR / RT-DETRv2: YOLOv12-S beats RT-DETR-R18 / RT-DETRv2-R18 while running 42% faster, using only 36% of the computation and 45% of the parameters. More comparisons are shown in Figure 1.","external_url":"https://arxiv.org/abs/2502.12524","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T07:45:28.843340+00:00","pith_arxiv_id":"2502.12524","created_at":"2026-05-10T05:41:02.097801+00:00","updated_at":"2026-05-25T07:45:28.843340+00:00","title_quality_ok":true,"display_title":"YOLOv12: Attention-Centric Real-Time Object Detectors","render_title":"YOLOv12: Attention-Centric Real-Time Object Detectors"},"hub":{"state":{"work_id":"b2da2ba7-83b7-4573-96e5-d6f2b8ef3897","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":35,"external_cited_by_count":null,"distinct_field_count":6,"first_pith_cited_at":"2025-01-25T09:24:14+00:00","last_pith_cited_at":"2026-05-20T09:26:47+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-03T16:56:13.042352+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"method","n":3},{"context_role":"baseline","n":2}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"use_method","n":3},{"context_polarity":"baseline","n":2}],"runs":{},"summary":{},"graph":{},"authors":[]}}