DeepAI AI Chat
Log In Sign Up

YOLOv4: Optimal Speed and Accuracy of Object Detection

04/23/2020
by   Alexey Bochkovskiy, et al.
Academia Sinica
73

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 https://github.com/AlexeyAB/darknet

READ FULL TEXT

page 6

page 8

page 11

page 12

page 13

11/16/2020

Scaled-YOLOv4: Scaling Cross Stage Partial Network

We show that the YOLOv4 object detection neural network based on the CSP...
09/19/2022

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

This study introduces a new normalization layer termed Batch Layer Norma...
11/20/2017

MegDet: A Large Mini-Batch Object Detector

The improvements in recent CNN-based object detection works, from R-CNN ...
11/27/2019

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

Neural networks have enabled state-of-the-art approaches to achieve incr...
01/15/2021

Dynamic Normalization

Batch Normalization has become one of the essential components in CNN. I...
05/21/2021

Maximum and Leaky Maximum Propagation

In this work, we present an alternative to conventional residual connect...
08/18/2021

Generalizing MLPs With Dropouts, Batch Normalization, and Skip Connections

A multilayer perceptron (MLP) is typically made of multiple fully connec...

Code Repositories

darknet

Convolutional Neural Networks


view repo

pytorch-YOLOv4

PyTorch ,ONNX and TensorRT implementation of YOLOv4


view repo

YOLO-Reproduce-Summary

YOLO reproduce summary (now based on YOLOv3)


view repo

yolodet-pytorch

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


view repo

car_detection_forza_horizon

Object detection of Forza Horizon 4 gameplay video


view repo