YOLOv4融合多种技术，在实时检测中实现高精度与强适应性。
YOLOv4: A Breakthrough in Real-Time Object Detection
- 融合Mosaic数据增强与多尺度训练，提升复杂场景检测能力。
- 在Tesla V100上达43.5% AP，推理速度超65帧/秒。
- 适合需要高效、低成本部署的实时目标检测应用。
YOLOv4通过结合先进的回归（边界框定位）与分类（物体类别识别）技术，在Darknet框架下实现了COCO数据集上的最佳性能。为提升准确率与适应性，引入Cross mini-Batch Normalization、Cross-Stage-Partial connections、Self-Adversarial Training、Weighted Residual Connections、CIoU损失函数、Mosaic数据增强及DropBlock正则化。借助Mosaic增强与多分辨率训练，YOLOv4在多样化场景中表现优异，在Tesla V100上达到43.5% AP（AP50为65.7%），推理速度约65帧/秒，兼顾效率、成本与实际环境适应性。
原文摘要 · Abstract (English)
YOLOv4 achieved the best performance on the COCO dataset by combining advanced techniques for regression (bounding box positioning) and classification (object class identification) using the Darknet framework. To enhance accuracy and adaptability, it employs Cross mini-Batch Normalization, Cross-Stage-Partial-connections, Self-Adversarial-Training, and Weighted-Residual-Connections, as well as CIoU loss, Mosaic data augmentation, and DropBlock regularization. With Mosaic augmentation and multi-resolution training, YOLOv4 achieves superior detection in diverse scenarios, attaining 43.5\% AP (in contrast, 65.7\% AP50) on a Tesla V100 at ~65 frames per second, ensuring efficiency, affordability, and adaptability for real-world environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。