刚刚！YOLOv4重磅推出！

最新推荐文章于 2025-12-22 14:05:40 发布

原创最新推荐文章于 2025-12-22 14:05:40 发布 · 1.7k 阅读

0 ·

CC 4.0 BY-SA版权

学习记录

文章标签：

#微软 #go #html #github #html5

YoloV4在arxiv上发布最新版本，并同步更新了Github代码。该研究结合多种新特性如Weighted-Residual-Connections (WRC)、Cross-Stage-Partial-connections (CSP)等，在MSCOCO数据集上实现了43.5% AP的实时精度(~65FPS)。

部署运行你感兴趣的模型镜像

点上方蓝字Python人工智能与深度学习社区获取更多干货

在右上方 ··· 设为星标 ★，第一时间获取资源

刚刚YoloV4在arxiv更新了！

https://arxiv.org/abs/2004.10934v1

https://github.com/AlexeyAB/darknet

Github代码也更新了！

摘要：

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% AP (65.7% AP50) for the MS COCO dataset at a realtime speed of ~65 FPS on Tesla V100.

不对论文解读了，以免有失偏颇，欢迎大家留言分享对此论文的点评！