DeepAI AI Chat
Log In Sign Up

YOLOv4: Optimal Speed and Accuracy of Object Detection

by   Alexey Bochkovskiy, et al.
Academia Sinica

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 for the MS COCO dataset at a realtime speed of  65 FPS on Tesla V100. Source code is at


page 6

page 8

page 11

page 12

page 13


Scaled-YOLOv4: Scaling Cross Stage Partial Network

We show that the YOLOv4 object detection neural network based on the CSP...

Batch Layer Normalization, A new normalization layer for CNNs and RNN

This study introduces a new normalization layer termed Batch Layer Norma...

MegDet: A Large Mini-Batch Object Detector

The improvements in recent CNN-based object detection works, from R-CNN ...

CSPNet: A New Backbone that can Enhance Learning Capability of CNN

Neural networks have enabled state-of-the-art approaches to achieve incr...

Dynamic Normalization

Batch Normalization has become one of the essential components in CNN. I...

Maximum and Leaky Maximum Propagation

In this work, we present an alternative to conventional residual connect...

SNDCNN: Self-normalizing deep CNNs with scaled exponential linear units for speech recognition

Very deep CNNs achieve state-of-the-art results in both computer vision ...

Code Repositories


Convolutional Neural Networks

view repo


PyTorch ,ONNX and TensorRT implementation of YOLOv4

view repo


YOLO reproduce summary (now based on YOLOv3)

view repo


reproduce the YOLO series of papers in pytorch, including YOLOv4, PP-YOLO, YOLOv5,YOLOv3, etc.

view repo


Object detection of Forza Horizon 4 gameplay video

view repo