YOLO（You Only Look Once）论文详解

最新推荐文章于 2025-05-21 16:00:45 发布

原创

最新推荐文章于 2025-05-21 16:00:45 发布 · 1.5k 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#目标检测 #人工智能 #YOLO #one-stage #计算机视觉

YOLO是一种将物体检测视为回归问题的快速、统一的检测系统，通过单个神经网络直接预测图像中的边界框和类概率。相较于其他方法，YOLO更快，但在定位精度上可能略有不足，且在小目标检测上表现不佳。YOLO通过全局图像输入利用上下文信息，减少背景误报，且在跨领域泛化方面表现出色。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

论文地址：https://arxiv.org/pdf/1506.02640.pdf

代码地址：

https://github.com/hizhangp/yolo_tensorflow

https://github.com/gliese581gg/YOLO_tensorflow

https://github.com/thtrieu/darkflow

Abstract

We present YOLO, a new approach to object detection. Prior work on object detection repurposes classiﬁers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance.

Our uniﬁed architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from