mlsanityData to 14 Oct 2026

YOLO9000: Better, Faster, Stronger

arXiv 1612.08242 ↗First posted 25 Dec 2016cs.CVcited by 1,431

Not on the map. Why?

Abstract (arXiv)

We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. At 67 FPS, YOLOv2 gets 76.8 mAP on VOC 2007. At 40 FPS, YOLOv2 gets 78.6 mAP, outperforming state-of-the-art methods like Faster RCNN with ResNet and SSD while still running significantly faster. Finally we propose a method to jointly train on object detection and classification. Using this method we train YOLO9000 simultaneously on the COCO detection dataset and the ImageNet classification dataset. Our joint training allows YOLO9000 to predict detections for object classes that don't have labelled detection data. We validate our approach on the ImageNet detection task. YOLO9000 gets 19.7 mAP on the ImageNet detection validation set despite only having detection data for 44 of the 200 classes. On the 156 classes not in COCO, YOLO9000 gets 16.0 mAP. But YOLO can detect more than just 200 classes; it predicts detections for more than 9000 different object categories. And it still runs in real-time.

Key facts. Cited by 1,431 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Dec 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 380; 2022: 333; 2023: 302; 2024: 209; 2025: 143; 2026: 64.

1,431 papers.

Sort:

By area:

  1. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  2. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  3. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 982
  4. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
  5. 2021MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformercited by 642
  6. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 614
  7. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 533
  8. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 515
  9. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 503
  10. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 488
  11. 2021FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detectioncited by 447
  12. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 425
38 more
  1. 2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 425
  2. 2021Conditional DETR for Fast Training Convergencecited by 424
  3. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  4. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  5. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 305
  6. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 275
  7. 2021H2O: Two Hands Manipulating Objects for First Person Interaction Recognitioncited by 254
  8. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  9. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  10. 2021LLVIP: A Visible-infrared Paired Dataset for Low-light Visioncited by 231
  11. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 204
  12. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 195
  13. 2021Probabilistic and Geometric Depth: Detecting Objects in Perspectivecited by 191
  14. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
  15. 2021Multimodal Virtual Point 3D Detectioncited by 166
  16. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 151
  17. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  18. 2022Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detectioncited by 146
  19. 2021Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphscited by 144
  20. 2022PromptDet: Towards Open-vocabulary Detection using Uncurated Imagescited by 133
  21. 2021Probabilistic two-stage detectioncited by 130
  22. 2021OW-DETR: Open-world Detection Transformercited by 129
  23. 2021Efficient DETR: Improving End-to-End Object Detector with Dense Priorcited by 128
  24. 2021Simple multi-dataset detectioncited by 127
  25. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  26. 2021Cross-Domain Adaptive Teacher for Object Detectioncited by 126
  27. 2022Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalizationcited by 123
  28. 2021You Only Look One-level Featurecited by 116
  29. 2021Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challengescited by 115
  30. 2021General Instance Distillation for Object Detectioncited by 114
  31. 2021Learning Open-World Object Proposals without Learning to Classifycited by 109
  32. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  33. 2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
  34. 2021Recent advances and clinical applications of deep learning in medical image analysiscited by 104
  35. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 98
  36. 2022Adversarial Texture for Fooling Person Detectors in the Physical Worldcited by 96
  37. 2022Learning Object-Language Alignments for Open-Vocabulary Object Detectioncited by 96
  38. 2023Rethinking Model Ensemble in Transfer-based Adversarial Attackscited by 89

50 most cited of 1,431 All 1,431 (JSON)