YOLOv12: Attention-Centric Real-Time Object Detectors
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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
16 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale cites Language Models are Few-Shot Learners
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites Training data-efficient image transformers & distillation through attention
- MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image Generation cites High-Resolution Image Synthesis with Latent Diffusion Models
- Training data-efficient image transformers & distillation through attention cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Cited by top-tier papers16
- Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object DetectionZhangchi Hu, Peixi Wu, Jie Chen, Huyue Zhu et al.ACM MM 2025 · 25 citations
- YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time DetectionXu Lin, Jinlong Peng, Zhenye Gan, Jiawen Zhu et al.CVPR 2026 · 22 citations
- 3DRealCar: An In-the-Wild RGB-D Car Dataset with 360-Degree ViewsXiaobiao Du, Yida Wang, Haiyang Sun, Zhuojie Wu et al.ICCV 2025 · 10 citations
- MultiBanana: A Challenging Benchmark for Multi-Reference Text-to-Image GenerationYuta Oshima, Daiki Miyake, Kohsei Matsutani, Yusuke Iwasawa et al.CVPR 2026 · 10 citations
- MoCha: End-to-End Video Character Replacement without Structural GuidanceZhengbo Xu, Jie Ma, Ziheng Wang, Zhan Peng et al.CVPR 2026 · 9 citations
Builds on35
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Training data-efficient image transformers & distillation through attentionHugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa et al.ICML 2021 · 8,974 citations
Related papers
- YOLO-ULM: Ultra-Lightweight Models for Real-Time Object DetectionShasha Han, Chong Li, Xinning Wang, Xuebo LiCVPR 2026
- DETRs Beat YOLOs on Real-time Object DetectionYian Zhao, Wenyu Lv, Shangliang Xu, Jinman Wei et al.CVPR 2024 · 3,046 citations
- YOLOv10: Real-Time End-to-End Object DetectionAo Wang, Hui Chen, Lihao Liu, Kai Chen et al.NeurIPS 2024 · 6,113 citations
- Don't Let the Information Slip AwayTaozhe Li, Guansu Wang, Bo Yu, Yiming Liu, Wei SunCVPR Findings 2026
- YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object DetectorsChien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark LiaoCVPR 2023
