Data to 7 Oct 2026

YOLOv4: Optimal Speed and Accuracy of Object Detection

arXiv 2004.10934 ↗First posted 23 Apr 2020cs.CV eess.IVcited by 1,624

Not on the map. Why?

Cited by 32 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

There are a huge number of features which are said to improve Convolutional Neural Network (CNN) accuracy. Practical testing of combinations of such features on large datasets, and theoretical justification of the result, is required. Some features operate on certain models exclusively and for certain problems exclusively, or only for small-scale datasets; while some features, such as batch-normalization and residual-connections, are applicable to the majority of models, tasks, and datasets. We assume that such universal features include Weighted-Residual-Connections (WRC), Cross-Stage-Partial-connections (CSP), Cross mini-Batch Normalization (CmBN), Self-adversarial-training (SAT) and Mish-activation. We use new features: WRC, CSP, CmBN, SAT, Mish activation, Mosaic data augmentation, CmBN, DropBlock regularization, and CIoU loss, and combine some of them to achieve state-of-the-art results: 43.5% AP (65.7% AP50) for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100. Source code is at https://github.com/AlexeyAB/darknet

Key facts. Cited by 1,624 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 289; 2022: 366; 2023: 333; 2024: 305; 2025: 201; 2026: 130.

1,624 papers.

Sort:

By area:

2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,306
2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
2023GLIGEN: Open-Set Grounded Text-to-Image Generationcited by 774
2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
2022DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETRcited by 569
2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
2021Conditional DETR for Fast Training Convergencecited by 422

38 more

2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 422
2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 414
2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
2023BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusioncited by 280
2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
2023LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generationcited by 258
2021LLVIP: A Visible-infrared Paired Dataset for Low-light Visioncited by 229
2022DyLoRA: Parameter Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptationcited by 229
2022CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusioncited by 222
2023UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wildcited by 197
2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
2023DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Modelscited by 162
2021Activation Functions in Deep Learning: A Comprehensive Survey and Benchmarkcited by 153
2023DDFM: Denoising Diffusion Model for Multi-Modality Image Fusioncited by 153
2023A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAScited by 149
2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
2021Probabilistic two-stage detectioncited by 130
2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 119
2021You Only Look One-level Featurecited by 116
2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112
2021Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentationcited by 107
2024BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at oncecited by 107
2021DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detectioncited by 106
2022Slicing Aided Hyper Inference and Fine-tuning for Small Object Detectioncited by 101
2023Equivariant Multi-Modality Image Fusioncited by 98
2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
2022A Comprehensive Survey of Image Augmentation Techniques for Deep Learningcited by 95
2021CAT: Cross Attention in Vision Transformercited by 92
2023Rethinking Model Ensemble in Transfer-based Adversarial Attackscited by 88
2024RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformercited by 88
2021Cross-Modality Fusion Transformer for Multispectral Object Detectioncited by 86
2021Image-Adaptive YOLO for Object Detection in Adverse Weather Conditionscited by 85
2021TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarioscited by 83
2021YOLOP: You Only Look Once for Panoptic Driving Perceptioncited by 82
2022Source-Free Unsupervised Domain Adaptation: A Surveycited by 79
2023Deep Directly-Trained Spiking Neural Networks for Object Detectioncited by 76
2023ICAFusion: Iterative Cross-Attention Guided Feature Fusion for Multispectral Object Detectioncited by 76

50 most cited of 1,624 All 1,624 (JSON)