mlsanityData to 7 Oct 2026

YOLOX: Exceeding YOLO Series in 2021

arXiv 2107.08430 ↗First posted 18 Jul 2021cs.CVcited by 1,064

Not on the map. Why?

Abstract (arXiv)

In this report, we present some experienced improvements to YOLO series, forming a new high-performance detector -- YOLOX. We switch the YOLO detector to an anchor-free manner and conduct other advanced detection techniques, i.e., a decoupled head and the leading label assignment strategy SimOTA to achieve state-of-the-art results across a large scale range of models: For YOLO-Nano with only 0.91M parameters and 1.08G FLOPs, we get 25.3% AP on COCO, surpassing NanoDet by 1.8% AP; for YOLOv3, one of the most widely used detectors in industry, we boost it to 47.3% AP on COCO, outperforming the current best practice by 3.0% AP; for YOLOX-L with roughly the same amount of parameters as YOLOv4-CSP, YOLOv5-L, we achieve 50.0% AP on COCO at a speed of 68.9 FPS on Tesla V100, exceeding YOLOv5-L by 1.8% AP. Further, we won the 1st Place on Streaming Perception Challenge (Workshop on Autonomous Driving at CVPR 2021) using a single YOLOX-L model. We hope this report can provide useful experience for developers and researchers in practical scenes, and we also provide deploy versions with ONNX, TensorRT, NCNN, and Openvino supported. Source code is at https://github.com/Megvii-BaseDetection/YOLOX.

Key facts. Cited by 1,064 papers in the map (data through 7 Oct 2026). Builds on 35 of its 41 references that are in the map. First posted on arXiv 18 Jul 2021.

Builds on

35 of 41 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  7. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  8. 2018YOLOv3: An Incremental Improvementcited by 2,652
  9. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  10. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  11. 2017Accurate, Large Minibatch SGD: Training ImageNet in 1 Hourcited by 1,479
  12. 2016YOLO9000: Better, Faster, Strongercited by 1,429
23 more
  1. 2019Objects as Pointscited by 1,172
  2. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  3. 2018Path Aggregation Network for Instance Segmentationcited by 796
  4. 2018CornerNet: Detecting Objects as Paired Keypointscited by 763
  5. 2017Focal Loss for Dense Object Detectioncited by 749
  6. 2020Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentationcited by 595
  7. 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 539
  8. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  9. 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
  10. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 177
  11. 2020Probabilistic Anchor Assignment with IoU Prediction for Object Detectioncited by 150
  12. 2021You Only Look One-level Featurecited by 116
  13. 2020AutoAssign: Differentiable Label Assignment for Dense Object Detectioncited by 100
  14. 2019Rethinking Classification and Localization for Object Detectioncited by 98
  15. 2019FreeAnchor: Learning to Match Anchors for Visual Object Detectioncited by 90
  16. 2020Revisiting the Sibling Head in Object Detectorcited by 82
  17. 2020End-to-End Object Detection with Fully Convolutional Networkcited by 70
  18. 2019Learning Spatial Fusion for Single-Shot Object Detectioncited by 59
  19. 2019Bag of Freebies for Training Object Detection Neural Networkscited by 47
  20. 2021PP-YOLOv2: A Practical Object Detectorcited by 30
  21. 2021IQDet: Instance-wise Quality Distribution Sampling for Object Detectioncited by 20
  22. 2021LLA: Loss-aware Label Assignment for Dense Pedestrian Detectioncited by 7
  23. 2021Object Detection Made Simpler by Eliminating Heuristic NMScited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 152; 2023: 250; 2024: 299; 2025: 200; 2026: 145.

1,064 papers.

Sort:

By area:

  1. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  2. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
  3. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  4. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  5. 2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
  6. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  7. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  8. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  9. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
  10. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  11. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  12. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
38 more
  1. 2023Effective Whole-body Pose Estimation with Two-stages Distillationcited by 307
  2. 2023Fast Segment Anythingcited by 286
  3. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  4. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 213
  5. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  6. 2022AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Timecited by 199
  7. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  8. 2023Universal Instance Perception as Object Discovery and Retrievalcited by 190
  9. 2024ColPali: Efficient Document Retrieval with Vision Language Modelscited by 190
  10. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
  11. 2022Recurrent Vision Transformers for Object Detection with Event Camerascited by 158
  12. 2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
  13. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  14. 2021Focal and Global Knowledge Distillation for Detectorscited by 138
  15. 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenescited by 130
  16. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
  17. 2022MeMOT: Multi-Object Tracking with Memorycited by 113
  18. 2022In Defense of Online Models for Video Instance Segmentationcited by 97
  19. 2022Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignmentcited by 96
  20. 2022Towards Grand Unification of Object Trackingcited by 93
  21. 2023TRACE: 5D Temporal Regression of Avatars with Dynamic Cameras in 3D Environmentscited by 89
  22. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 86
  23. 2021TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarioscited by 83
  24. 2022CLRNet: Cross Layer Refinement Network for Lane Detectioncited by 82
  25. 2022SoccerNet-Tracking: Multiple Object Tracking Dataset and Benchmark in Soccer Videoscited by 80
  26. 2022PP-YOLOE: An evolved version of YOLOcited by 75
  27. 2024State Space Models for Event Camerascited by 75
  28. 2023GET: Group Event Transformer for Event-Based Visioncited by 73
  29. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  30. 2023BOP Challenge 2022 on Detection, Segmentation and Pose Estimation of Specific Rigid Objectscited by 70
  31. 2023Far3D: Expanding the Horizon for Surround-view 3D Object Detectioncited by 70
  32. 2024DEIM: DETR with Improved Matching for Fast Convergencecited by 67
  33. 2022YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Losscited by 66
  34. 2022Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Spacecited by 66
  35. 2023Hybrid-SORT: Weak Cues Matter for Online Multi-Object Trackingcited by 66
  36. 2021Low-light Image Enhancement via Breaking Down the Darknesscited by 65
  37. 2023MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Trackingcited by 64
  38. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64

50 most cited of 1,064 All 1,064 (JSON)