# Scaled-YOLOv4: Scaling Cross Stage Partial Network

arXiv: https://arxiv.org/abs/2011.08036 · HTML: https://mlsanity.com/paper/2011.08036/

## Key facts

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

## Built on by (most cited first, 30 of 211)

- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [YOLOv10: Real-Time End-to-End Object Detection](https://mlsanity.com/paper/2405.14458/) (2024)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection](https://mlsanity.com/paper/2106.00666/) (2021)
- [A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS](https://mlsanity.com/paper/2304.00501/) (2023)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions](https://mlsanity.com/paper/2206.08171/) (2022)
- [A Survey of Modern Deep Learning based Object Detection Models](https://mlsanity.com/paper/2104.11892/) (2021)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [CAT: Cross Attention in Vision Transformer](https://mlsanity.com/paper/2106.05786/) (2021)
- [You Only Learn One Representation: Unified Network for Multiple Tasks](https://mlsanity.com/paper/2105.04206/) (2021)
- [TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios](https://mlsanity.com/paper/2108.11539/) (2021)
- [YOLOP: You Only Look Once for Panoptic Driving Perception](https://mlsanity.com/paper/2108.11250/) (2021)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [PP-YOLOE: An evolved version of YOLO](https://mlsanity.com/paper/2203.16250/) (2022)
- [Continental-Scale Building Detection from High Resolution Satellite Imagery](https://mlsanity.com/paper/2107.12283/) (2021)
- [GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021](https://mlsanity.com/paper/2202.11983/) (2022)
- [DAMO-YOLO : A Report on Real-Time Object Detection Design](https://mlsanity.com/paper/2211.15444/) (2022)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes](https://mlsanity.com/paper/2108.04814/) (2021)
- [MS-DETR: Efficient DETR Training with Mixed Supervision](https://mlsanity.com/paper/2401.03989/) (2024)
- [BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training](https://mlsanity.com/paper/2203.13249/) (2022)
- [NMS Strikes Back](https://mlsanity.com/paper/2212.06137/) (2022)
- [YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection](https://mlsanity.com/paper/2308.05480/) (2023)
- [Designing Network Design Strategies Through Gradient Path Analysis](https://mlsanity.com/paper/2211.04800/) (2022)
- [PP-YOLOv2: A Practical Object Detector](https://mlsanity.com/paper/2104.10419/) (2021)
- [Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation](https://mlsanity.com/paper/2408.04804/) (2024)

## 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.