Methods › Computer Vision › One-Stage Object Detection Models › YOLOv4

YOLOv4

100 papers tagged archive 2025-07-28

Introduced by Alexey Bochkovskiy et al. in YOLOv4: Optimal Speed and Accuracy of Object Detection

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

YOLOv4 is a one-stage object detection model that improves on YOLOv3 with several bags of tricks and modules introduced in the literature. The components section below details the tricks and modules used.

PaperSourceSee Code · AlexeyAB/darknet

Papers archive 2025-07-28

30 shown of 100, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 123 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Object Detection59
object-detection56
Object29
Real-Time Object Detection9
Data Augmentation8
GPU8
Deep Learning7
Autonomous Driving6
Segmentation5
Semantic Segmentation5
Transfer Learning5
2D Object Detection3
Domain Adaptation3
Image Classification3
Instance Segmentation3
License Plate Detection3
Object Tracking3
Optical Character Recognition3
Optical Character Recognition (OCR)3
Self-Driving Cars3

Usage over time archive 2025-07-28

Papers per year tagged with YOLOv4: 2016 to 2025, peak 33 33 0 2016: 1 paper 2016 2017: 0 papers 2017 2018: 0 papers 2018 2019: 0 papers 2019 2020: 14 papers 2020 2021: 23 papers 2021 2022: 33 papers 2022 2023: 17 papers 2023 2024: 5 papers 2024 2025: 7 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (100 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

One-Stage Object Detection ModelsObject Detection Models

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections