mlsanityData to 7 Oct 2026

Scaled-YOLOv4: Scaling Cross Stage Partial Network

arXiv 2011.08036 ↗First posted 16 Nov 2020cs.CV cs.LGcited by 211

Not on the map. Why?

Abstract (arXiv)

We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining optimal speed and accuracy. We propose a network scaling approach that modifies not only the depth, width, resolution, but also structure of the network. YOLOv4-large model achieves state-of-the-art results: 55.5% AP (73.4% AP50) for the MS COCO dataset at a speed of ~16 FPS on Tesla V100, while with the test time augmentation, YOLOv4-large achieves 56.0% AP (73.3 AP50). To the best of our knowledge, this is currently the highest accuracy on the COCO dataset among any published work. The YOLOv4-tiny model achieves 22.0% AP (42.0% AP50) at a speed of 443 FPS on RTX 2080Ti, while by using TensorRT, batch size = 4 and FP16-precision the YOLOv4-tiny achieves 1774 FPS.

Key facts. Cited by 211 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Nov 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 44; 2022: 65; 2023: 48; 2024: 29; 2025: 15; 2026: 10.

211 papers.

Sort:

By area:

  1. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  2. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  3. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  4. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  5. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  6. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  7. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  8. 2021Probabilistic two-stage detectioncited by 130
  9. 2021Simple multi-dataset detectioncited by 126
  10. 2022K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditionscited by 107
  11. 2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
  12. 2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
38 more
  1. 2021CAT: Cross Attention in Vision Transformercited by 92
  2. 2021You Only Learn One Representation: Unified Network for Multiple Taskscited by 86
  3. 2021TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarioscited by 83
  4. 2021YOLOP: You Only Look Once for Panoptic Driving Perceptioncited by 82
  5. 2021CBNet: A Composite Backbone Network Architecture for Object Detectioncited by 77
  6. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  7. 2021Continental-Scale Building Detection from High Resolution Satellite Imagerycited by 50
  8. 2022GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021cited by 46
  9. 2022DAMO-YOLO : A Report on Real-Time Object Detection Designcited by 38
  10. 2021Disentangle Your Dense Object Detectorcited by 37
  11. 2021R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenescited by 36
  12. 2024MS-DETR: Efficient DETR Training with Mixed Supervisioncited by 34
  13. 2022BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-trainingcited by 33
  14. 2022NMS Strikes Backcited by 33
  15. 2023YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detectioncited by 33
  16. 2022Designing Network Design Strategies Through Gradient Path Analysiscited by 32
  17. 2021PP-YOLOv2: A Practical Object Detectorcited by 30
  18. 2024Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computationcited by 29
  19. 2021DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attackscited by 28
  20. 2022Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectorscited by 28
  21. 2022Machine Learning for Microcontroller-Class Hardware: A Reviewcited by 28
  22. 2022No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objectscited by 26
  23. 2021Simple Training Strategies and Model Scaling for Object Detectioncited by 25
  24. 2022YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perceptioncited by 25
  25. 2022The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Countingcited by 24
  26. 2022The 6th AI City Challengecited by 23
  27. 2023DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasetscited by 23
  28. 2021BoxeR: Box-Attention for 2D and 3D Transformerscited by 22
  29. 2021Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimationcited by 20
  30. 2021Revitalizing Optimization for 3D Human Pose and Shape Estimation: A Sparse Constrained Formulationcited by 19
  31. 2022Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Surveycited by 17
  32. 2023Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?cited by 17
  33. 2022Interspace Pruning: Using Adaptive Filter Representations to Improve Training of Sparse CNNscited by 16
  34. 2023DynamicDet: A Unified Dynamic Architecture for Object Detectioncited by 15
  35. 2023Physical Adversarial Attacks for Surveillance: A Surveycited by 15
  36. 2024ESOD: Efficient Small Object Detection on High-Resolution Imagescited by 15
  37. 2021Non-deep Networkscited by 14
  38. 2023You Only Look at Once for Real-time and Generic Multi-Taskcited by 14

50 most cited of 211 All 211 (JSON)