YOLOv three: An Incremental Improvement

YOLOv three: An Incremental Improvement

Abstract

We present some updates to YOLO! We made a bunch of little design changes to make it better. We also trained this new network that's pretty swell. It's a little bigger than last time but more accurate. It's still fast though, don't worry. At three hundred twenty by three hundred twenty YOLOv three runs in twenty-two milliseconds at twenty-eight point two mAP, as accurate as SSD but three times faster. When we look at the old point five IOU mAP detection metric YOLOv three is quite good. It achieves fifty-seven point nine AP fifty in fifty-one milliseconds on a Titan X, compared to fifty-seven point five AP fifty in one hundred ninety-eight milliseconds by RetinaNet, similar performance but three point eight times faster. As always, all the code is online.

One. Introduction

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.

Actually, that's what brings us here today. We have a camera-ready deadline and we need to cite some of the random updates I made to YOLO but we don't have a source. So get ready for a TECH REPORT!

The great thing about tech reports is that they don't need intros, y'all know why we're here. So the end of this introduction will signpost for the rest of the paper. First we'll tell you what the deal is with YOLOv three. Then we'll tell you how we do. We'll also tell you about some things we tried that didn't work. Finally we'll contemplate what this all means.