一、摘要

 *We present YOLO, a new approach to object detection.Prior work on object detection repurposes classififiers 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 unifified 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 natural images to other domains like artwork*

将目标检测问题当作回归问题解决——损失函数使用平方和误差损失函数

优点：

不需要提取候选框（单阶段检测算法）
速度非常快，实时，端到端
捕捉全图上下文信息，将背景误检为目标的概率小
迁移泛化能力好，eg.在自然图像上训练算法，算法在艺术图像的数据集上的检测效果依然不错

缺点：

MAP比较低