图 1:YOLO9000。YOLO9000 可以实时检测许多目标类别。
All of our code and pre-trained models are available online
at http://pjreddie.com/yolo9000/.
我 们 的 所 有 代 码 和 预 训 练 模 型 都 可 在 线 获 得 :
http://pjreddie.com/yolo9000/。
2. Better
YOLO suffers from a variety of shortcomings relative to state-of-the-
art detection systems. Error analysis of YOLO compared to Fast R-CNN
shows that YOLO makes a significant number of localization errors.
Furthermore, YOLO has relatively low recall compared to region proposal-
based methods. Thus we focus mainly on improving recall and localization
while maintaining classification accuracy.
2. 更好
与最先进的检测系统相比,YOLO 有许多缺点。YOLO 与 Fast R-
CNN 的误差分析比较表明,YOLO 存在大量的定位误差。此外,与
基于 region proposal 的方法相比,YOLO 召回率相对较低。因此,我
们主要侧重于提高召回率和改进目标精确定位,同时保持分类准确性。
Computer vision generally trends towards larger, deeper networks [6]
[18] [17]. Better performance often hinges on training larger networks or
ensembling multiple models together. However, with YOLOv2 we want a
more accurate detector that is still fast. Instead of scaling up our network,
we simplify the network and then make the representation easier to learn.
We pool a variety of ideas from past work with our own novel concepts to