【目标检测-YOLO】YOLOv3

YOLOv3: An Incremental Improvement

Abstract

At 320*320 YOLOv3 runs in 22 ms at 28.2 mAP, as accurate as SSD but three times faster. When we look at the old .5 IOU mAP detection metric YOLOv3 is quite good. It achieves 57.9 AP50 in 51 ms on a Titan X, compared to 57.5 AP50 in 198 ms by RetinaNet, similar performance but 3.8x faster.

依旧是效果说话，320*320 YOLOv3 和SSD精度差不多，但是快三倍。AP50上和 RetinaNet性能接近但是快3.8x。

1. Introduction

没啥意思

2. The Deal

YOLOv3使用的前人技巧，提出了一个好的分类网络。

图1. YOLOv3 推理快

2.1. Bounding Box Prediction

和v2一样还是使用 anchor，还是尺寸聚类。