YOLOv4: Optimal Speed and Accuracy of Object Detection

04/23/2020
by   Alexey Bochkovskiy, et al.
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

research
11/16/2020

Scaled-YOLOv4: Scaling Cross Stage Partial Network

We show that the YOLOv4 object detection neural network based on the CSP...
research
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...
research
11/20/2017

MegDet: A Large Mini-Batch Object Detector

The improvements in recent CNN-based object detection works, from R-CNN ...
research
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...
research
01/15/2021

Dynamic Normalization

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

Maximum and Leaky Maximum Propagation

In this work, we present an alternative to conventional residual connect...
research
10/04/2019

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 ...

Please sign up or login with your details

Forgot password? Click here to reset