YOLO 系列物体检测算法--YOLO v

YOLO v3 的文章写的比较随意，是以类似技术报告的形式记录了一些改进工作。文章开头就很清奇：

Sometimes you just kinda phone it in for a year, you know? I didn’t do a whole lot of research this year. Spent a lot of time on Twitter. Played around with GANs a little. I had a little momentum left over from last year; I managed to make some improvements to YOLO. But, honestly, nothing like super interesting, just a bunch of small changes that make it better. I also helped out with other people’s research a little.

结尾部分也挺有意思，很讽刺，似乎也很深刻：

But maybe a better question is: “What are we going to do with these detectors now that we have them?” A lot of the people doing this research are at Google and Facebook. I guess at least we know the technology is in good hands and definitely won’t be used to harvest your personal information and sell it to.... wait, you’re saying that’s exactly what it will be used for?? Oh.
...
Well the other people heavily funding vision research are the military and they’ve never done anything horrible like killing lots of people with new technology oh wait.....
...
I have a lot of hope that most of the people using computer vision are just doing happy, good stuff with it, like counting the number of zebras in a national park, or tracking their cat as it wanders around their house. But computer vision is already being put to questionable use and as researchers we have a responsibility to at least consider the harm our work might be doing and think of ways to mitigate it. We owe the world that much.
...
In closing, do not @ me. (Because I finally quit Twitter).

除了训练细节方面比较琐碎的改进，YOLO v3 最主要的改进是采用了新的基础网络作特征提取，将 ResNet 的思想引入了原本的 Darknet-19 中，得到 53 层卷积层的网络。

It has 53 convolutional layers so we call it ... wait for it ... Darknet-53.

作者似乎没少看 《How I Met Your Mother》，连写文章也要模仿一下。。。

最后 YOLO v3 在检测速度和准确度方面都比较出色。尽管 RetinaNet 在准确度方面比 YOLO v3 好，但是检测速度方面，YOLO v3 碾压所有对手。所以在之后的自动驾驶环境中，我们会优先考虑用 YOLO v3 做目标检测工作。

yolo3.PNG

yolo3-2.PNG