mlsanityData to 7 Oct 2026

PP-YOLOv2: A Practical Object Detector

arXiv 2104.10419 ↗First posted 21 Apr 2021cs.CVcited by 30

Not on the map. Why?

Abstract (arXiv)

Being effective and efficient is essential to an object detector for practical use. To meet these two concerns, we comprehensively evaluate a collection of existing refinements to improve the performance of PP-YOLO while almost keep the infer time unchanged. This paper will analyze a collection of refinements and empirically evaluate their impact on the final model performance through incremental ablation study. Things we tried that didn't work will also be discussed. By combining multiple effective refinements, we boost PP-YOLO's performance from 45.9% mAP to 49.5% mAP on COCO2017 test-dev. Since a significant margin of performance has been made, we present PP-YOLOv2. In terms of speed, PP-YOLOv2 runs in 68.9FPS at 640x640 input size. Paddle inference engine with TensorRT, FP16-precision, and batch size = 1 further improves PP-YOLOv2's infer speed, which achieves 106.5 FPS. Such a performance surpasses existing object detectors with roughly the same amount of parameters (i.e., YOLOv4-CSP, YOLOv5l). Besides, PP-YOLOv2 with ResNet101 achieves 50.3% mAP on COCO2017 test-dev. Source code is at https://github.com/PaddlePaddle/PaddleDetection.

Key facts. Cited by 30 papers in the map (data through 7 Oct 2026). Builds on 25 of its 27 references that are in the map. First posted on arXiv 21 Apr 2021.

Builds on

25 of 27 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2017Squeeze-and-Excitation Networkscited by 4,763
  7. 2018YOLOv3: An Incremental Improvementcited by 2,652
  8. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  9. 2017Deformable Convolutional Networkscited by 1,481
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  11. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  12. 2018Path Aggregation Network for Instance Segmentationcited by 796
13 more
  1. 2014Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognitioncited by 719
  2. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  3. 2018Bag of Tricks for Image Classification with Convolutional Neural Networkscited by 430
  4. 2018An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solutioncited by 302
  5. 2018DropBlock: A regularization method for convolutional networkscited by 261
  6. 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
  7. 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
  8. 2019Mish: A Self Regularized Non-Monotonic Activation Functioncited by 141
  9. 2019Learning Spatial Fusion for Single-Shot Object Detectioncited by 59
  10. 2019CBNet: A Novel Composite Backbone Network Architecture for Object Detectioncited by 44
  11. 2020PP-YOLO: An Effective and Efficient Implementation of Object Detectorcited by 44
  12. 2021Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbonescited by 15
  13. 2019HoughNet: neural network architecture for vanishing points detectioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 6; 2023: 8; 2024: 7; 2025: 2; 2026: 2.

30 papers.

Sort:

  1. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  2. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  3. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  4. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  5. 2024RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervisioncited by 31
  6. 2022SoccerNet 2022 Challenges Resultscited by 28
  7. 2021PP-PicoDet: A Better Real-Time Object Detector on Mobile Devicescited by 25
  8. 2022PP-StructureV2: A Stronger Document Analysis Systemcited by 18
  9. 2022Continuous Human Action Recognition for Human-Machine Interaction: A Reviewcited by 10
  10. 2021Waste detection in Pomerania: non-profit project for detecting waste in environmentcited by 8
  11. 2021TCCT: Tightly-Coupled Convolutional Transformer on Time Series Forecastingcited by 8
  12. 2023Deep Learning Approaches for Seizure Video Analysis: A Reviewcited by 6
18 more
  1. 2024YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systemscited by 6
  2. 2022DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attentioncited by 5
  3. 2023YOLOCS: Object Detection based on Dense Channel Compression for Feature Spatial Solidificationcited by 4
  4. 2025A Decade of You Only Look Once (YOLO) for Object Detection: A Reviewcited by 3
  5. 2023A Survey of Advanced Computer Vision Techniques for Sportscited by 2
  6. 2024GUI Element Detection Using SOTA YOLO Deep Learning Modelscited by 2
  7. 20212nd Place Solution for Waymo Open Dataset Challenge -- Real-time 2D Object Detectioncited by 1
  8. 2023CST-YOLO: A Novel Method for Blood Cell Detection Based on Improved YOLOv7 and CNN-Swin Transformercited by 1
  9. 2024FA-YOLO: Research On Efficient Feature Selection YOLO Improved Algorithm Based On FMDS and AGMF Modulescited by 1
  10. 2022YOLOSA: Object detection based on 2D local feature superimposed self-attentioncited by 0
  11. 2023MMDR: A Result Feature Fusion Object Detection Approach for Autonomous Systemcited by 0
  12. 2023High-Performance Fine Defect Detection in Artificial Leather Using Dual Feature Pool Object Detectioncited by 0
  13. 2024Surveying You Only Look Once (YOLO) Multispectral Object Detection Advancements, Applications And Challengescited by 0
  14. 2024WoodYOLO: A Novel Object Detector for Wood Species Detection in Microscopic Imagescited by 0
  15. 20243A-YOLO: New Real-Time Object Detectors with Triple Discriminative Awareness and Coordinated Representationscited by 0
  16. 2025YOLO-PRO: Enhancing Instance-Specific Object Detection with Full-Channel Global Self-Attentioncited by 0
  17. 2026YOLO-DS: Fine-Grained Feature Decoupling via Dual-Statistic Synergy Operator for Object Detectioncited by 0
  18. 2026A Study on Real-time Object Detection using Deep Learningcited by 0