YOLOv4: Optimal Speed and Accuracy of Object Detection
Alexey Bochkovskiy∗ Chien-Yao Wang∗ Institute of Information Science Academia Sinica, Taiwan Hong-Yuan Mark Liao Institute of Information Science Academia Sinica, Taiwan
Abstract
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 real-time speed of $\sim$ 65 FPS on Tesla V100. Source code is at https://github.com/AlexeyAB/darknet.
中文速览
卷积神经网络目标检测领域存在大量所谓"能提升精度"的技巧，但缺乏对它们组合效果的系统验证。YOLOv4在这一背景下，系统梳理并筛选出一批真正具有普适性的训练策略（如马赛克数据增强、DropBlock正则化、CIoU损失等"免费午餐"）和推理增强模块（如加权残差连接、跨阶段局部连接CSP、跨小批量归一化CmBN、Mish激活函数等），将其有机融入以CSPDarknet53为骨干的单阶段检测框架。最终在MS COCO数据集上以约65 FPS的实时速度达到43.5% AP（AP50为65.7%），超越此前所有实时检测器。这项工作的重要意义在于，整个训练过程只需一块普通消费级GPU（如GTX 1080 Ti）即可完成，让高精度实时目标检测真正走向大众可用，而非仅限于多卡大算力的研究环境。
原文 arXiv:2004.10934;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2004.10934v1